mirror of
https://github.com/wassname/Open-Assistant.git
synced 2026-06-30 16:40:05 +08:00
merge
This commit is contained in:
Sotirios Anagnostidis
@@ -15,6 +15,9 @@ jobs:
|
||||
- uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: "3.10"
|
||||
- uses: actions/setup-node@v3
|
||||
with:
|
||||
node-version: 16
|
||||
|
||||
- run: cd oasst-shared && pip install -e .
|
||||
|
||||
@@ -22,9 +25,14 @@ jobs:
|
||||
|
||||
- run: cd backend && pip install -r requirements.txt
|
||||
|
||||
- run: cd website && npm ci
|
||||
|
||||
- run: ./scripts/backend-development/start-mock-server.sh
|
||||
|
||||
- name: Run contract tests
|
||||
- name: Run Python OasstApiClient contract tests
|
||||
run: ./scripts/oasst-shared-development/test.sh
|
||||
|
||||
- name: Run JavaScript OasstApiClient contract tests
|
||||
run: ./scripts/frontend-development/run-contract-test.sh
|
||||
|
||||
- run: ./scripts/backend-development/stop-mock-server.sh
|
||||
|
||||
@@ -26,7 +26,7 @@
|
||||
#
|
||||
# /WARNING!
|
||||
|
||||
exclude: build|stubs|^bot/templates/$
|
||||
exclude: build|stubs|^bot/templates/$|openassistant/templates
|
||||
|
||||
repos:
|
||||
- repo: https://github.com/pre-commit/pre-commit-hooks
|
||||
|
||||
+110
@@ -0,0 +1,110 @@
|
||||
# I’m in! Now what?
|
||||
|
||||
[Join the OpenAssistant Contributors Discord Server!](https://ykilcher.com/open-assistant-discord),
|
||||
this is for work coordination.
|
||||
|
||||
[Join the LAION Discord Server!](https://discord.com/invite/mVcgxMPD7e), it has
|
||||
a dedicated channel and is more public.
|
||||
|
||||
[and / or the YK Discord Server](https://ykilcher.com/discord), also has a
|
||||
dedicated, but not as active, channel.
|
||||
|
||||
[Visit the Notion](https://ykilcher.com/open-assistant)
|
||||
|
||||
### Taking on Tasks
|
||||
|
||||
We have a growing task list
|
||||
[of issues](https://github.com/LAION-AI/Open-Assistant/issues). Find an issue
|
||||
that appeals to you and make a comment that you'd like to work on it. Include in
|
||||
your comment a brief description of how you'll solve the problem and if there
|
||||
are any open questions you want to discuss. Once a project coordinator has
|
||||
assigned the issue to you, start working on it.
|
||||
|
||||
If the issue is currently unclear but you are interested, please post in Discord
|
||||
and someone can help clarify the issue with more detail.
|
||||
|
||||
**Always Welcome:** Documentation markdowns in `docs/`, docstrings, diagrams of
|
||||
the system architecture, and other documentation.
|
||||
|
||||
### Submitting Work
|
||||
|
||||
We're all working on different parts of Open Assistant together. To make
|
||||
contributions smoothly we recommend the following:
|
||||
|
||||
1. [Fork this project repository](https://docs.github.com/en/get-started/quickstart/fork-a-repo)
|
||||
and clone it to your local machine. (Read more
|
||||
[About Forks](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/about-forks))
|
||||
1. Before working on any changes, try to
|
||||
[sync the forked repository](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork)
|
||||
to keep it up-to-date with the upstream repository.
|
||||
1. Work on a small focused change that only touches on a few files.
|
||||
1. Run `pre-commit` and make sure all files have formatting fixed. This
|
||||
simplifies life for reviewers.
|
||||
1. Package up a small bit of work that solves part of the problem
|
||||
[into a Pull Request](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request-from-a-fork)
|
||||
and
|
||||
[send it out for review](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/requesting-a-pull-request-review).
|
||||
1. If you're lucky, we can merge your change into `main` without any problems.
|
||||
If there's changes to files you're working on, resolve them by:
|
||||
1. First try rebase as suggested
|
||||
[in these instructions](https://timwise.co.uk/2019/10/14/merge-vs-rebase/#should-you-rebase).
|
||||
1. If rebase feels too painful, merge as suggested
|
||||
[in these instructions](https://timwise.co.uk/2019/10/14/merge-vs-rebase/#should-you-merge).
|
||||
1. Once you've resolved any conflicts, finish the review and merge into `main`.
|
||||
1. Merge in your change and move onto a new issue or the second step of your
|
||||
current issue.
|
||||
|
||||
Additionally, if someone is working on an issue that interests you, ask if they
|
||||
need help on it or would like suggestions on how to approach the issue. If so,
|
||||
share wildly. If they seem to have a good handle on it, let them work on their
|
||||
solution until a challenge comes up.
|
||||
|
||||
### When does a review finish
|
||||
|
||||
A review finishes when all blocking comments are addressed and at least one
|
||||
owning reviewer has approved the PR. Be sure to acknowledge any non-blocking
|
||||
comments either by making the request change, explaining why it's not being
|
||||
addressed now, or filing an issue to handle it later.
|
||||
|
||||
## Developer Setup
|
||||
|
||||
Work is organized in the
|
||||
[project board](https://github.com/orgs/LAION-AI/projects/3).
|
||||
|
||||
**Anything that is in the `Todo` column and not assigned, is up for grabs.
|
||||
Meaning we'd be happy for anyone to do these tasks.**
|
||||
|
||||
If you want to work on something, assign yourself to it or write a comment that
|
||||
you want to work on it and what you plan to do.
|
||||
|
||||
- To get started with development, if you want to work on the backend, have a
|
||||
look at `scripts/backend-development/README.md`.
|
||||
- If you want to work on any frontend, have a look at
|
||||
`scripts/frontend-development/README.md` to make a backend available.
|
||||
|
||||
There is also a minimal implementation of a frontend in the `text-frontend`
|
||||
folder.
|
||||
|
||||
We are using Python 3.10 for the backend.
|
||||
|
||||
Check out the
|
||||
[High-Level Protocol Architecture](https://www.notion.so/High-Level-Protocol-Architecture-6f1fd3551da74213b560ead369f132dc)
|
||||
|
||||
### Website
|
||||
|
||||
The website is built using Next.js and is in the `website` folder.
|
||||
|
||||
### Pre-commit
|
||||
|
||||
Install `pre-commit` and run `pre-commit install` to install the pre-commit
|
||||
hooks.
|
||||
|
||||
In case you haven't done this, have already committed, and CI is failing, you
|
||||
can run `pre-commit run --all-files` to run the pre-commit hooks on all files.
|
||||
|
||||
### Deployment
|
||||
|
||||
Upon making a release on GitHub, all docker images are automatically built and
|
||||
pushed to ghcr.io. The docker images are tagged with the release version, and
|
||||
the `latest` tag. Further, the ansible playbook in `ansible/dev.yaml` is run to
|
||||
automatically deploy the built release to the dev machine.
|
||||
@@ -1,7 +1,34 @@
|
||||
# Open-Assistant
|
||||
<h1 align="center">
|
||||
<span>Open-Assistant</span>
|
||||
<img width="auto" height="50px" src="https://github.com/LAION-AI/Open-Assistant/blob/main/assets/logo_crop.png"/>
|
||||
</h1>
|
||||
|
||||
Open Assistant is a project meant to give everyone access to a great chat based
|
||||
large language model.
|
||||
<div align="center">
|
||||
|
||||
<a href=""></a>
|
||||
<a href=""></a>
|
||||
<a href=""></a>
|
||||
<a href=""></a>
|
||||
<a href=""></a>
|
||||
|
||||
</div>
|
||||
|
||||
# Table of Contents
|
||||
|
||||
- [What is Open Assistant?](#what-is-open-assistant)
|
||||
- [Do you want to try it out?](#do-you-want-to-try-it-out)
|
||||
- [The Plan](#the-plan)
|
||||
- [The Vision](#the-vision)
|
||||
- [How can you help?](#how-can-you-help)
|
||||
- [I’m in! How do I contribute?](CONTRIBUTING.md)
|
||||
|
||||
---
|
||||
|
||||
## What is Open Assistant?
|
||||
|
||||
<p align="center">
|
||||
Open Assistant is a project meant to give everyone access to a great chat based large language model.
|
||||
</p>
|
||||
|
||||
We believe that by doing this we will create a revolution in innovation in
|
||||
language. In the same way that stable-diffusion helped the world make art and
|
||||
@@ -14,7 +41,7 @@ If you are interested in taking a look at the current state of the project, you
|
||||
can set up an entire stack needed to run **Open-Assistant**, including the
|
||||
website, backend, and associated dependent services.
|
||||
|
||||
To start the demo, run this in the root directory of the repository:
|
||||
##### To start the demo, run this in the root directory of the repository:
|
||||
|
||||
```sh
|
||||
docker compose up --build
|
||||
@@ -23,22 +50,21 @@ docker compose up --build
|
||||
Then, navigate to `http://localhost:3000` (It may take some time to boot up) and
|
||||
interact with the website.
|
||||
|
||||
**Note:** When logging in via email, navigate to `http://localhost:1080` to get
|
||||
the magic email login link.
|
||||
> **Note:** When logging in via email, navigate to `http://localhost:1080` to
|
||||
> get the magic email login link.
|
||||
|
||||
**Note:** If you would like to run this in a standardized development
|
||||
environment (a
|
||||
["devcontainer"](https://code.visualstudio.com/docs/devcontainers/containers))
|
||||
using
|
||||
[vscode locally](https://code.visualstudio.com/docs/devcontainers/create-dev-container#_create-a-devcontainerjson-file)
|
||||
or in a web browser using
|
||||
[GitHub Codespaces](https://github.com/features/codespaces), you can use the
|
||||
provided [`.devcontainer`](.devcontainer/) folder.
|
||||
> **Note:** If you would like to run this in a standardized development
|
||||
> environment (a
|
||||
> ["devcontainer"](https://code.visualstudio.com/docs/devcontainers/containers))
|
||||
> using
|
||||
> [vscode locally](https://code.visualstudio.com/docs/devcontainers/create-dev-container#_create-a-devcontainerjson-file)
|
||||
> or in a web browser using
|
||||
> [GitHub Codespaces](https://github.com/features/codespaces), you can use the
|
||||
> provided [`.devcontainer`](.devcontainer/) folder.
|
||||
|
||||
## The Plan
|
||||
|
||||
We want to get to an initial MVP as fast as possible, by following the 3-steps
|
||||
outlined in the InstructGPT paper.
|
||||
##### We want to get to an initial MVP as fast as possible, by following the 3-steps outlined in the InstructGPT paper.
|
||||
|
||||
1. Collect high-quality human generated Instruction-Fulfillment samples
|
||||
(prompt + response), goal >50k. We design a crowdsourced process to collect
|
||||
@@ -80,113 +106,4 @@ All open source projects begin with people like you. Open source is the belief
|
||||
that if we collaborate we can together gift our knowledge and technology to the
|
||||
world for the benefit of humanity.
|
||||
|
||||
## I’m in! Now what?
|
||||
|
||||
[Join the OpenAssistant Contributors Discord Server!](https://ykilcher.com/open-assistant-discord),
|
||||
this is for work coordination.
|
||||
|
||||
[Join the LAION Discord Server!](https://discord.com/invite/mVcgxMPD7e), it has
|
||||
a dedicated channel and is more public.
|
||||
|
||||
[and / or the YK Discord Server](https://ykilcher.com/discord), also has a
|
||||
dedicated, but not as active, channel.
|
||||
|
||||
[Visit the Notion](https://ykilcher.com/open-assistant)
|
||||
|
||||
### Taking on Tasks
|
||||
|
||||
We have a growing task list
|
||||
[of issues](https://github.com/LAION-AI/Open-Assistant/issues). Find an issue
|
||||
that appeals to you and make a comment that you'd like to work on it. Include in
|
||||
your comment a brief description of how you'll solve the problem and if there
|
||||
are any open questions you want to discuss. Once a project coordinator has
|
||||
assigned the issue to you, start working on it.
|
||||
|
||||
If the issue is currently unclear but you are interested, please post in Discord
|
||||
and someone can help clarify the issue with more detail.
|
||||
|
||||
**Always Welcome:** Documentation markdowns in `docs/`, docstrings, diagrams of
|
||||
the system architecture, and other documentation.
|
||||
|
||||
### Submitting Work
|
||||
|
||||
We're all working on different parts of Open Assistant together. To make
|
||||
contributions smoothly we recommend the following:
|
||||
|
||||
1. [Fork this project repository](https://docs.github.com/en/get-started/quickstart/fork-a-repo)
|
||||
and clone it to your local machine. (Read more
|
||||
[About Forks](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/about-forks))
|
||||
1. Before working on any changes, try to
|
||||
[sync the forked repository](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork)
|
||||
to keep it up-to-date with the upstream repository.
|
||||
1. Work on a small focused change that only touches on a few files.
|
||||
1. Run `pre-commit` and make sure all files have formatting fixed. This
|
||||
simplifies life for reviewers.
|
||||
1. Package up a small bit of work that solves part of the problem
|
||||
[into a Pull Request](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request-from-a-fork)
|
||||
and
|
||||
[send it out for review](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/requesting-a-pull-request-review).
|
||||
1. If you're lucky, we can merge your change into `main` without any problems.
|
||||
If there's changes to files you're working on, resolve them by:
|
||||
1. First try rebase as suggested
|
||||
[in these instructions](https://timwise.co.uk/2019/10/14/merge-vs-rebase/#should-you-rebase).
|
||||
1. If rebase feels too painful, merge as suggested
|
||||
[in these instructions](https://timwise.co.uk/2019/10/14/merge-vs-rebase/#should-you-merge).
|
||||
1. Once you've resolved any conflicts, finish the review and merge into `main`.
|
||||
1. Merge in your change and move onto a new issue or the second step of your
|
||||
current issue.
|
||||
|
||||
Additionally, if someone is working on an issue that interests you, ask if they
|
||||
need help on it or would like suggestions on how to approach the issue. If so,
|
||||
share wildly. If they seem to have a good handle on it, let them work on their
|
||||
solution until a challenge comes up.
|
||||
|
||||
### When does a review finish
|
||||
|
||||
A review finishes when all blocking comments are addressed and at least one
|
||||
owning reviewer has approved the PR. Be sure to acknowledge any non-blocking
|
||||
comments either by making the request change, explaining why it's not being
|
||||
addressed now, or filing an issue to handle it later.
|
||||
|
||||
## Developer Setup
|
||||
|
||||
Work is organized in the
|
||||
[project board](https://github.com/orgs/LAION-AI/projects/3).
|
||||
|
||||
**Anything that is in the `Todo` column and not assigned, is up for grabs.
|
||||
Meaning we'd be happy for anyone to do these tasks.**
|
||||
|
||||
If you want to work on something, assign yourself to it or write a comment that
|
||||
you want to work on it and what you plan to do.
|
||||
|
||||
- To get started with development, if you want to work on the backend, have a
|
||||
look at `scripts/backend-development/README.md`.
|
||||
- If you want to work on any frontend, have a look at
|
||||
`scripts/frontend-development/README.md` to make a backend available.
|
||||
|
||||
There is also a minimal implementation of a frontend in the `text-frontend`
|
||||
folder.
|
||||
|
||||
We are using Python 3.10 for the backend.
|
||||
|
||||
Check out the
|
||||
[High-Level Protocol Architecture](https://www.notion.so/High-Level-Protocol-Architecture-6f1fd3551da74213b560ead369f132dc)
|
||||
|
||||
### Website
|
||||
|
||||
The website is built using Next.js and is in the `website` folder.
|
||||
|
||||
### Pre-commit
|
||||
|
||||
Install `pre-commit` and run `pre-commit install` to install the pre-commit
|
||||
hooks.
|
||||
|
||||
In case you haven't done this, have already committed, and CI is failing, you
|
||||
can run `pre-commit run --all-files` to run the pre-commit hooks on all files.
|
||||
|
||||
### Deployment
|
||||
|
||||
Upon making a release on GitHub, all docker images are automatically built and
|
||||
pushed to ghcr.io. The docker images are tagged with the release version, and
|
||||
the `latest` tag. Further, the ansible playbook in `ansible/dev.yaml` is run to
|
||||
automatically deploy the built release to the dev machine.
|
||||
Check out our [contributing guide](CONTRIBUTING.md) to get started.
|
||||
|
||||
@@ -54,6 +54,7 @@
|
||||
DEBUG_ALLOW_ANY_API_KEY: "true"
|
||||
DEBUG_USE_SEED_DATA: "true"
|
||||
MAX_WORKERS: "1"
|
||||
RATE_LIMIT: "false"
|
||||
ports:
|
||||
- 8080:8080
|
||||
|
||||
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 24 KiB |
@@ -1,3 +1,4 @@
|
||||
__pycache__
|
||||
.env
|
||||
notes.txt
|
||||
venv
|
||||
|
||||
+4
-2
@@ -11,10 +11,12 @@ Example contents of a `.env` file for the backend:
|
||||
```
|
||||
DATABASE_URI="postgresql://<username>:<password>@<host>/<database_name>"
|
||||
BACKEND_CORS_ORIGINS=["http://localhost", "http://localhost:4200", "http://localhost:3000", "http://localhost:8080", "https://localhost", "https://localhost:4200", "https://localhost:3000", "https://localhost:8080", "http://dev.oasst.laion.ai", "https://stag.oasst.laion.ai", "https://oasst.laion.ai"]
|
||||
|
||||
REDIS_HOST=localhost
|
||||
REDIS_PORT=6379
|
||||
```
|
||||
|
||||
## Running the REST Server locally for development
|
||||
|
||||
Have a look into the main `README.md` file for more information on how to set up
|
||||
the backend for development.
|
||||
the backend for development. Use the scripts within the
|
||||
scripts/backend-development folder to run the BE API locally.
|
||||
|
||||
@@ -0,0 +1,46 @@
|
||||
"""added MessageTreeState table
|
||||
|
||||
Revision ID: d4161e384f83
|
||||
Revises: 8d269bc4fdbd
|
||||
Create Date: 2023-01-05 11:44:02.630633
|
||||
|
||||
"""
|
||||
import sqlalchemy as sa
|
||||
import sqlmodel
|
||||
from alembic import op
|
||||
from sqlalchemy.dialects import postgresql
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision = "d4161e384f83"
|
||||
down_revision = "8d269bc4fdbd"
|
||||
branch_labels = None
|
||||
depends_on = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"message_tree_state",
|
||||
sa.Column("id", postgresql.UUID(as_uuid=True), server_default=sa.text("gen_random_uuid()"), nullable=False),
|
||||
sa.Column("created_date", sa.DateTime(), server_default=sa.text("CURRENT_TIMESTAMP"), nullable=False),
|
||||
sa.Column("deleted", sa.Boolean(), server_default=sa.text("false"), nullable=False),
|
||||
sa.Column("message_tree_id", sqlmodel.sql.sqltypes.GUID(), nullable=False),
|
||||
sa.Column("state", sqlmodel.sql.sqltypes.AutoString(length=128), nullable=False),
|
||||
sa.Column("goal_tree_size", sa.Integer(), nullable=False),
|
||||
sa.Column("current_num_non_filtered_messages", sa.Integer(), nullable=False),
|
||||
sa.Column("max_depth", sa.Integer(), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id"),
|
||||
)
|
||||
op.create_index(
|
||||
op.f("ix_message_tree_state_message_tree_id"), "message_tree_state", ["message_tree_id"], unique=False
|
||||
)
|
||||
op.create_index("ix_message_tree_state_tree_id", "message_tree_state", ["message_tree_id"], unique=True)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_index("ix_message_tree_state_tree_id", table_name="message_tree_state")
|
||||
op.drop_index(op.f("ix_message_tree_state_message_tree_id"), table_name="message_tree_state")
|
||||
op.drop_table("message_tree_state")
|
||||
# ### end Alembic commands ###
|
||||
+42
@@ -0,0 +1,42 @@
|
||||
"""removed date_created and deleted flag from message_tree_state
|
||||
|
||||
Revision ID: 3b0adfadbef9
|
||||
Revises: d4161e384f83
|
||||
Create Date: 2023-01-05 13:46:11.338655
|
||||
|
||||
"""
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
from sqlalchemy.dialects import postgresql
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision = "3b0adfadbef9"
|
||||
down_revision = "d4161e384f83"
|
||||
branch_labels = None
|
||||
depends_on = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_column("message_tree_state", "deleted")
|
||||
op.drop_column("message_tree_state", "created_date")
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.add_column(
|
||||
"message_tree_state",
|
||||
sa.Column(
|
||||
"created_date",
|
||||
postgresql.TIMESTAMP(),
|
||||
server_default=sa.text("CURRENT_TIMESTAMP"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
)
|
||||
op.add_column(
|
||||
"message_tree_state",
|
||||
sa.Column("deleted", sa.BOOLEAN(), server_default=sa.text("false"), autoincrement=False, nullable=False),
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
+2
-2
@@ -230,8 +230,8 @@ if __name__ == "__main__":
|
||||
help="Dumps the openapi schema to stdout",
|
||||
action=argparse.BooleanOptionalAction,
|
||||
)
|
||||
parser.add_argument("--host", help="The host to run the server")
|
||||
parser.add_argument("--port", help="The port to run the server")
|
||||
parser.add_argument("--host", help="The host to run the server", default="0.0.0.0")
|
||||
parser.add_argument("--port", help="The port to run the server", default=8080)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
|
||||
@@ -2,6 +2,7 @@ from fastapi import APIRouter
|
||||
from oasst_backend.api.v1 import (
|
||||
frontend_messages,
|
||||
frontend_users,
|
||||
hugging_face,
|
||||
leaderboards,
|
||||
messages,
|
||||
stats,
|
||||
@@ -19,3 +20,4 @@ api_router.include_router(users.router, prefix="/users", tags=["users"])
|
||||
api_router.include_router(frontend_users.router, prefix="/frontend_users", tags=["frontend_users"])
|
||||
api_router.include_router(stats.router, prefix="/stats", tags=["stats"])
|
||||
api_router.include_router(leaderboards.router, prefix="/experimental/leaderboards", tags=["leaderboards"])
|
||||
api_router.include_router(hugging_face.router, prefix="/hf", tags=["hugging_face"])
|
||||
|
||||
@@ -0,0 +1,37 @@
|
||||
from enum import Enum
|
||||
from typing import List
|
||||
|
||||
from fastapi import APIRouter, Depends
|
||||
from oasst_backend.api import deps
|
||||
from oasst_backend.models import ApiClient
|
||||
from oasst_backend.schemas.hugging_face import ToxicityClassification
|
||||
from oasst_backend.utils.hugging_face import HuggingFaceAPI
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
class HF_url(str, Enum):
|
||||
HUGGINGFACE_TOXIC_ROBERTA = "https://api-inference.huggingface.co/models/unitary/multilingual-toxic-xlm-roberta"
|
||||
|
||||
|
||||
@router.get("/text_toxicity")
|
||||
async def get_text_toxicity(
|
||||
msg: str,
|
||||
api_client: ApiClient = Depends(deps.get_trusted_api_client),
|
||||
) -> List[List[ToxicityClassification]]:
|
||||
"""Get the Message Toxicity from HuggingFace Roberta model.
|
||||
|
||||
Args:
|
||||
msg (str): the message that we want to analyze.
|
||||
api_client (ApiClient, optional): authentification of the user of the request.
|
||||
Defaults to Depends(deps.get_trusted_api_client).
|
||||
|
||||
Returns:
|
||||
ToxicityClassification: the score of toxicity of the message.
|
||||
"""
|
||||
|
||||
api_url: str = HF_url.HUGGINGFACE_TOXIC_ROBERTA.value
|
||||
hugging_face_api = HuggingFaceAPI(api_url)
|
||||
response = await hugging_face_api.post(msg)
|
||||
|
||||
return response
|
||||
@@ -24,14 +24,13 @@ def generate_task(
|
||||
match request.type:
|
||||
case protocol_schema.TaskRequestType.random:
|
||||
logger.info("Frontend requested a random task.")
|
||||
while request.type == protocol_schema.TaskRequestType.random:
|
||||
disabled_tasks = (
|
||||
protocol_schema.TaskRequestType.summarize_story,
|
||||
protocol_schema.TaskRequestType.rate_summary,
|
||||
)
|
||||
request.type = random.choice(
|
||||
tuple(set(protocol_schema.TaskRequestType).difference(disabled_tasks))
|
||||
).value
|
||||
disabled_tasks = (
|
||||
protocol_schema.TaskRequestType.random,
|
||||
protocol_schema.TaskRequestType.summarize_story,
|
||||
protocol_schema.TaskRequestType.rate_summary,
|
||||
)
|
||||
candidate_tasks = set(protocol_schema.TaskRequestType).difference(disabled_tasks)
|
||||
request.type = random.choice(tuple(candidate_tasks)).value
|
||||
return generate_task(request, pr)
|
||||
|
||||
# AKo: Summary tasks are currently disabled/supported, we focus on the conversation tasks.
|
||||
|
||||
@@ -22,6 +22,8 @@ class Settings(BaseSettings):
|
||||
DEBUG_SKIP_API_KEY_CHECK: bool = False
|
||||
DEBUG_USE_SEED_DATA: bool = False
|
||||
|
||||
HUGGING_FACE_API_KEY: str = ""
|
||||
|
||||
@validator("DATABASE_URI", pre=True)
|
||||
def assemble_db_connection(cls, v: Optional[str], values: Dict[str, Any]) -> Any:
|
||||
if isinstance(v, str):
|
||||
|
||||
@@ -2,6 +2,7 @@ from .api_client import ApiClient
|
||||
from .journal import Journal, JournalIntegration
|
||||
from .message import Message
|
||||
from .message_reaction import MessageReaction
|
||||
from .message_tree_state import MessageTreeState
|
||||
from .task import Task
|
||||
from .text_labels import TextLabels
|
||||
from .user import User
|
||||
@@ -13,6 +14,7 @@ __all__ = [
|
||||
"UserStats",
|
||||
"Message",
|
||||
"MessageReaction",
|
||||
"MessageTreeState",
|
||||
"Task",
|
||||
"TextLabels",
|
||||
"Journal",
|
||||
|
||||
@@ -0,0 +1,44 @@
|
||||
from enum import Enum
|
||||
from typing import Optional
|
||||
from uuid import UUID, uuid4
|
||||
|
||||
import sqlalchemy as sa
|
||||
import sqlalchemy.dialects.postgresql as pg
|
||||
from sqlmodel import Field, Index, SQLModel
|
||||
|
||||
# The types of States a message tree can have.
|
||||
|
||||
|
||||
class States(Enum):
|
||||
INITIAL = "initial"
|
||||
BREEDING_PHASE = "breeding_phase"
|
||||
RANKING_PHASE = "ranking_phase"
|
||||
READY_FOR_SCORING = "ready_for_scoring"
|
||||
CHILDREN_SCORED = "children_scored"
|
||||
FINAL = "final"
|
||||
|
||||
|
||||
VALID_STATES = (
|
||||
States.INITIAL,
|
||||
States.BREEDING_PHASE,
|
||||
States.RANKING_PHASE,
|
||||
States.READY_FOR_SCORING,
|
||||
States.CHILDREN_SCORED,
|
||||
States.FINAL,
|
||||
)
|
||||
|
||||
|
||||
class MessageTreeState(SQLModel, table=True):
|
||||
__tablename__ = "message_tree_state"
|
||||
__table_args__ = (Index("ix_message_tree_state_tree_id", "message_tree_id", unique=True),)
|
||||
|
||||
id: Optional[UUID] = Field(
|
||||
sa_column=sa.Column(
|
||||
pg.UUID(as_uuid=True), primary_key=True, default=uuid4, server_default=sa.text("gen_random_uuid()")
|
||||
),
|
||||
)
|
||||
message_tree_id: UUID = Field(nullable=False, index=True)
|
||||
state: str = Field(nullable=False, max_length=128)
|
||||
goal_tree_size: int = Field(nullable=False)
|
||||
current_num_non_filtered_messages: int = Field(nullable=False)
|
||||
max_depth: int = Field(nullable=False)
|
||||
@@ -0,0 +1,6 @@
|
||||
from pydantic import BaseModel
|
||||
|
||||
|
||||
class ToxicityClassification(BaseModel):
|
||||
label: str
|
||||
score: float
|
||||
@@ -0,0 +1,51 @@
|
||||
from typing import Any, Dict
|
||||
|
||||
import aiohttp
|
||||
from oasst_backend.config import settings
|
||||
from oasst_shared.exceptions import OasstError, OasstErrorCode
|
||||
|
||||
|
||||
class HuggingFaceAPI:
|
||||
"""Class Object to make post calls to endpoints for inference in models hosted in HuggingFace"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
api_url: str,
|
||||
):
|
||||
|
||||
# The API endpoint we want to access
|
||||
self.api_url: str = api_url
|
||||
|
||||
# Access token for the api
|
||||
self.api_key: str = settings.HUGGING_FACE_API_KEY
|
||||
|
||||
# Headers going to be used
|
||||
self.headers: Dict[str, str] = {"Authorization": f"Bearer {self.api_key}"}
|
||||
|
||||
async def post(self, input: str) -> Any:
|
||||
"""Post request to the endpoint to get an inference
|
||||
|
||||
Args:
|
||||
input (str): the input that we will pass to the model
|
||||
|
||||
Raises:
|
||||
OasstError: in the case we get a bad response
|
||||
|
||||
Returns:
|
||||
inference: the inference we obtain from the model in HF
|
||||
"""
|
||||
|
||||
async with aiohttp.ClientSession() as session:
|
||||
payload: Dict[str, str] = {"inputs": input}
|
||||
|
||||
async with session.post(self.api_url, headers=self.headers, json=payload) as response:
|
||||
# If we get a bad response
|
||||
if response.status != 200:
|
||||
raise OasstError(
|
||||
"Response Error Detoxify HuggingFace", error_code=OasstErrorCode.HUGGINGFACE_API_ERROR
|
||||
)
|
||||
|
||||
# Get the response from the API call
|
||||
inference = await response.json()
|
||||
|
||||
return inference
|
||||
@@ -36,3 +36,4 @@ environments:
|
||||
secrets:
|
||||
# Note: URI, not URL.
|
||||
DATABASE_URI: /copilot/${COPILOT_APPLICATION_NAME}/${COPILOT_ENVIRONMENT_NAME}/secrets/API_DATABASE_URL
|
||||
REDIS_HOST: /copilot/${COPILOT_APPLICATION_NAME}/${COPILOT_ENVIRONMENT_NAME}/secrets/REDIS_HOST
|
||||
|
||||
@@ -29,8 +29,8 @@ from oasst_shared.schemas.protocol import TaskRequestType
|
||||
|
||||
plugin = lightbulb.Plugin("WorkPlugin")
|
||||
|
||||
MAX_TASK_TIME = 60 * 60 # 1 hour
|
||||
MAX_TASK_ACCEPT_TIME = 60 # 1 minute
|
||||
MAX_TASK_TIME = 60 * 60 # seconds
|
||||
MAX_TASK_ACCEPT_TIME = 60 * 10 # seconds
|
||||
|
||||
settings = Settings()
|
||||
|
||||
@@ -117,7 +117,7 @@ async def _handle_task(ctx: lightbulb.Context, task_type: TaskRequestType) -> No
|
||||
# Task action loop
|
||||
completed = False
|
||||
while not completed:
|
||||
await ctx.author.send(embed=plain_embed("Please type your response here"))
|
||||
await ctx.author.send(embed=plain_embed("Please type your response below:"))
|
||||
try:
|
||||
event = await ctx.bot.wait_for(
|
||||
hikari.DMMessageCreateEvent,
|
||||
|
||||
+11
-10
@@ -80,6 +80,7 @@ def initial_prompt_message(task: protocol_schema.InitialPromptTask) -> str:
|
||||
|
||||
{_h1("INITIAL PROMPT")}
|
||||
|
||||
|
||||
{_writing_prompt("Please provide an initial prompt to the assistant.")}
|
||||
{_hint(task.hint)}
|
||||
"""
|
||||
@@ -91,10 +92,10 @@ def rank_initial_prompts_message(task: protocol_schema.RankInitialPromptsTask) -
|
||||
|
||||
{_h1("RANK INITIAL PROMPTS")}
|
||||
|
||||
{_ranking_prompt("Reply with the numbers of best to worst prompts separated by commas (example: '4,1,3,2')")}
|
||||
|
||||
|
||||
{_ordered_list(task.prompts)}
|
||||
|
||||
{_ranking_prompt("Reply with the numbers of best to worst prompts separated by commas (example: '4,1,3,2')")}
|
||||
"""
|
||||
|
||||
|
||||
@@ -104,12 +105,12 @@ def rank_prompter_reply_message(task: protocol_schema.RankPrompterRepliesTask) -
|
||||
|
||||
{_h1("RANK PROMPTER REPLIES")}
|
||||
|
||||
{_ranking_prompt("Reply with the numbers of best to worst replies separated by commas (example: '4,1,3,2')")}
|
||||
|
||||
|
||||
{_conversation(task.conversation)}
|
||||
{_user(None)}
|
||||
{_ordered_list(task.replies)}
|
||||
|
||||
{_ranking_prompt("Reply with the numbers of best to worst replies separated by commas (example: '4,1,3,2')")}
|
||||
"""
|
||||
|
||||
|
||||
@@ -119,12 +120,12 @@ def rank_assistant_reply_message(task: protocol_schema.RankAssistantRepliesTask)
|
||||
|
||||
{_h1("RANK ASSISTANT REPLIES")}
|
||||
|
||||
{_ranking_prompt("Reply with the numbers of best to worst replies separated by commas (example: '4,1,3,2')")}
|
||||
|
||||
|
||||
{_conversation(task.conversation)}
|
||||
{_assistant(None)}
|
||||
{_ordered_list(task.replies)}
|
||||
|
||||
{_ranking_prompt("Reply with the numbers of best to worst replies separated by commas (example: '4,1,3,2')")}
|
||||
"""
|
||||
|
||||
|
||||
@@ -134,11 +135,11 @@ def prompter_reply_message(task: protocol_schema.PrompterReplyTask) -> str:
|
||||
|
||||
{_h1("PROMPTER REPLY")}
|
||||
|
||||
{_response_prompt("Please provide a reply to the assistant.")}
|
||||
|
||||
|
||||
{_conversation(task.conversation)}
|
||||
{_hint(task.hint)}
|
||||
|
||||
{_response_prompt("Please provide a reply to the assistant.")}
|
||||
"""
|
||||
|
||||
|
||||
@@ -147,10 +148,10 @@ def assistant_reply_message(task: protocol_schema.AssistantReplyTask) -> str:
|
||||
return f"""\
|
||||
{_h1("ASSISTANT REPLY")}
|
||||
|
||||
{_response_prompt("Please provide a reply to the assistant.")}
|
||||
|
||||
|
||||
{_conversation(task.conversation)}
|
||||
|
||||
{_response_prompt("Please provide an assistant reply to the prompter.")}
|
||||
"""
|
||||
|
||||
|
||||
|
||||
@@ -10,6 +10,9 @@ Also, the schemas are leaning heavily on the
|
||||
[OpenAssistant Data Structures](https://docs.google.com/presentation/d/1iaX_nxasVWlvPiSNs0cllR9L_1neZq0RJxd6MFEalUY/edit?usp=sharing)
|
||||
presentation.
|
||||
|
||||
_Note on conformity: be pragmatic and decide what makes sense 🙂 , it's more
|
||||
important that we move forward than cramming everything into a uniform thing._
|
||||
|
||||
## Data Schemas
|
||||
|
||||
### Main structure: conversation trees
|
||||
@@ -203,3 +206,27 @@ message RankingExample {
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
## Databases
|
||||
|
||||
Open-Assistant uses two databases, one for the backend and one for the frontend.
|
||||
Both are [PostgreSQL](https://www.postgresql.org/) databases which run in docker
|
||||
containers.
|
||||
|
||||
### Backend ER-Diagram
|
||||
|
||||
|
||||
|
||||
**Notes**
|
||||
|
||||
- In order for the diagram to not be too messy, foreign key connection to
|
||||
`api_client` are not shown
|
||||
- `frontend_message_id` references `id` of `taskInteraction` on the frontend
|
||||
|
||||
### Frontend ER-Diagram
|
||||
|
||||
|
||||
|
||||
**Notes**
|
||||
|
||||
- `id` of `registeredTask` references `id`of `message`on the backend
|
||||
|
||||
@@ -0,0 +1,421 @@
|
||||
# OpenAssistant Datasets
|
||||
|
||||
The datasets for this project are currently hosted as loading scripts on the
|
||||
[Open-Assistant organization](https://huggingface.co/OpenAssistant) the Hugging
|
||||
Face Hub. Each of them can be loaded by first installing the 🤗 Datasets
|
||||
library:
|
||||
|
||||
```bash
|
||||
python -m pip install datasets
|
||||
```
|
||||
|
||||
and then running:
|
||||
|
||||
```python
|
||||
from datasets import load_dataset
|
||||
|
||||
dataset = load_dataset("OpenAssistant/{dataset-name}")
|
||||
```
|
||||
|
||||
We use this GitHub repository to accept new submissions and standardize quality
|
||||
control. See the instructions below if you'd like to contribute a new dataset to
|
||||
the project.
|
||||
|
||||
## Adding a new dataset
|
||||
|
||||
### 0. Pre-Requisites
|
||||
|
||||
Install Git and create a GitHub account prior to implementing a dataset; you can
|
||||
follow instructions to install Git
|
||||
[here](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git).
|
||||
|
||||
You will also need at least Python 3.8+. If you are installing Python, we
|
||||
recommend downloading
|
||||
[Anaconda](https://docs.anaconda.com/anaconda/install/index.html) to curate a
|
||||
python environment with necessary packages. **We strongly recommend Python 3.8+
|
||||
for stability**.
|
||||
|
||||
### 1. **Fork the OpenAssistant repository**
|
||||
|
||||
Fork the
|
||||
`OpenAssistant`[repository](https://github.com/LAION-AI/Open-Assistant). To do
|
||||
this, click the link to the repository and click "Fork" in the upper-right
|
||||
corner. You should get an option to fork to your account, provided you are
|
||||
signed into Github.
|
||||
|
||||
After you fork, clone the repository locally. You can do so as follows:
|
||||
|
||||
```bash
|
||||
git clone git@github.com:<your_github_username>/OpenAssistant.git
|
||||
cd OpenAssistant # enter the directory
|
||||
```
|
||||
|
||||
Next, you want to set your `upstream` location to enable you to push/pull (add
|
||||
or receive updates). You can do so as follows:
|
||||
|
||||
```bash
|
||||
git remote add upstream git@github.com:LAION-AI/Open-Assistant.git
|
||||
```
|
||||
|
||||
You can optionally check that this was set properly by running the following
|
||||
command:
|
||||
|
||||
```bash
|
||||
git remote -v
|
||||
```
|
||||
|
||||
The output of this command should look as follows:
|
||||
|
||||
```bash
|
||||
origin git@github.com:<your_github_username>/Open-Assistant.git (fetch)
|
||||
origin git@github.com:<your_github_username>/Open-Assistant.git (push)
|
||||
upstream git@github.com:LAION-AI/Open-Assistant.git (fetch)
|
||||
upstream git@github.com:LAION-AI/Open-Assistant.git (push)
|
||||
```
|
||||
|
||||
If you do NOT have an `origin` for whatever reason, then run:
|
||||
|
||||
```bash
|
||||
git remote add origin git@github.com:<your_github_username>/OpenAssistant.git
|
||||
```
|
||||
|
||||
The goal of `upstream` is to keep your repository up-to-date to any changes that
|
||||
are made officially to the OpenAssistant repo. You can do this as follows by
|
||||
running the following commands:
|
||||
|
||||
```
|
||||
git fetch upstream
|
||||
git pull
|
||||
```
|
||||
|
||||
Provided you have no _merge conflicts_, this will ensure the repo stays
|
||||
up-to-date as you make changes. However, before you make changes, you should
|
||||
make a custom branch to implement your changes.
|
||||
|
||||
You can make a new branch as such:
|
||||
|
||||
```
|
||||
git checkout -b <dataset_name>
|
||||
```
|
||||
|
||||
<p style="color:red"> <b> Please do not make changes on the master branch! </b></p>
|
||||
|
||||
Always make sure you're on the right branch with the following command:
|
||||
|
||||
```
|
||||
git branch
|
||||
```
|
||||
|
||||
The correct branch will have a asterisk \* in front of it.
|
||||
|
||||
### 2. **Create a development environment**
|
||||
|
||||
You can make an environment in any way you choose to. We highlight two possible
|
||||
options:
|
||||
|
||||
#### 2a) Create a conda environment
|
||||
|
||||
The following instructions will create an Anaconda `openassistant` environment.
|
||||
|
||||
- Install [anaconda](https://docs.anaconda.com/anaconda/install/) for your
|
||||
appropriate operating system.
|
||||
- Run the following command while in the `biomedical` folder (you can pick your
|
||||
python version):
|
||||
|
||||
```bash
|
||||
conda create -n openassistant python=3.8 # Creates a conda env
|
||||
conda activate openassistant # Activate your conda environment
|
||||
cd openassistant
|
||||
pip install -r dev-requirements.txt # Install this while in the openassistant folder
|
||||
```
|
||||
|
||||
You can deactivate your environment at any time by either exiting your terminal
|
||||
or using `conda deactivate`.
|
||||
|
||||
#### 2b) Create a venv environment
|
||||
|
||||
Python 3.3+ has venv automatically installed; official information is found
|
||||
[here](https://packaging.python.org/en/latest/guides/installing-using-pip-and-virtual-environments/).
|
||||
|
||||
```
|
||||
python3 -m venv <your_env_name_here>
|
||||
source <your_env_name_here>/bin/activate # activate environment
|
||||
cd openassistant
|
||||
pip install -r dev-requirements.txt # Install this while in the openassistant folder
|
||||
```
|
||||
|
||||
Make sure your `pip` package points to your environment's source.
|
||||
|
||||
### 3. Prepare a folder in `datasets` for your dataloader
|
||||
|
||||
Make a new directory within the `openassistant/datasets` directory:
|
||||
|
||||
```bash
|
||||
mkdir openassistant/datasets/<dataset_name>
|
||||
```
|
||||
|
||||
**NOTE**: Please use snake_case, i.e. lowercase letters and underscores when
|
||||
choosing a `<dataset_name>`.
|
||||
|
||||
Add an `__init__.py` file to this directory:
|
||||
|
||||
```bash
|
||||
touch openassistant/datasets/<dataset_name>/__init__.py
|
||||
```
|
||||
|
||||
Next, copy the `template.py` script and `hub.py` module of `templates` into your
|
||||
dataset folder. The `template.py` script has "TODOs" to fill in for your
|
||||
dataloading script:
|
||||
|
||||
```bash
|
||||
cp templates/hub.py openassistant/datasets/<dataset_name>/
|
||||
cp templates/template.py openassistant/datasets/<dataset_name>/<dataset_name>.py
|
||||
```
|
||||
|
||||
#### (Optional) Prepare local dataset files
|
||||
|
||||
If your dataset files aren't publicly available via URLs (e.g. because you
|
||||
implemented a web scraper), you'll need to implement some extra logic to store
|
||||
and prepare the data locally prior to implementing a loading script in 🤗
|
||||
Datasets.
|
||||
|
||||
To do so, first copy the template script for dataset creation:
|
||||
|
||||
```bash
|
||||
cp templates/prepare.py openassistant/datasets/<dataset_name>/
|
||||
```
|
||||
|
||||
Next, implement any logic that is needed to prepare a local version of the
|
||||
dataset files (by convention we store them in `datasets/<dataset_name>/data/`).
|
||||
Add any extra dependencies to a `requirements.txt` file and provide instructions
|
||||
on how to prepare the dataset files in a README:
|
||||
|
||||
```bash
|
||||
touch openassistant/datasets/<dataset_name>/requirements.txt
|
||||
cp templates/README.py openassistant/datasets/<dataset_name>/
|
||||
```
|
||||
|
||||
**Note:** Do not commit any dataset files to the OpenAssistant repo - all data
|
||||
will be hosted on the Hugging Face Hub. This step is needed for the project's
|
||||
data admins to be able to replicate the dataset creation process before pushing
|
||||
to the Hub.
|
||||
|
||||
### 4. Implement your dataset
|
||||
|
||||
To implement your dataloader, you will need to follow `template.py` and fill in
|
||||
all necessary TODOs. There are three key methods that are important:
|
||||
|
||||
- `_info`: Specifies the schema of the expected dataloader
|
||||
- `_split_generators`: Downloads and extracts data for each split (e.g.
|
||||
train/val/test) or associate local data with each split.
|
||||
- `_generate_examples`: Create examples from data that conform to each schema
|
||||
defined in `_info`.
|
||||
|
||||
For the `_info_` function, you will need to define `features` for your
|
||||
`DatasetInfo` object. For each dataset config, choose the right schema from our
|
||||
list of examples. You can find the schemas in the
|
||||
[schemas directory](openassistant/utils/schemas/).
|
||||
|
||||
You will use this schema in the `_generate_examples` return value.
|
||||
|
||||
Populate the information in the dataset according to this schema; some fields
|
||||
may be empty.
|
||||
|
||||
#### Example scripts
|
||||
|
||||
TODO
|
||||
|
||||
#### Running & debugging
|
||||
|
||||
You can run your data loader script during development by appending the
|
||||
following statement to your code ([templates/template.py](templates/template.py)
|
||||
already includes this):
|
||||
|
||||
```python
|
||||
if __name__ == "__main__":
|
||||
datasets.load_dataset(__file__)
|
||||
```
|
||||
|
||||
If you want to use an interactive debugger during development, you will have to
|
||||
use `breakpoint()` instead of setting breakpoints directly in your IDE. Most
|
||||
IDEs will recognize the `breakpoint()` statement and pause there during
|
||||
debugging. If your preferred IDE doesn't support this, you can always run the
|
||||
script in your terminal and debug with `pdb`.
|
||||
|
||||
### 5. Check if your dataloader works
|
||||
|
||||
Make sure your dataset is implemented correctly by checking in python the
|
||||
following commands:
|
||||
|
||||
```python
|
||||
from datasets import load_dataset
|
||||
|
||||
data = load_dataset("openassistant/datasets/<dataset_name>/<dataset_name>.py", name="<dataset_name>_<schema>")
|
||||
```
|
||||
|
||||
Run these commands from the top level of the `OpenAssistant` repo.
|
||||
|
||||
### 6. Create a dataset card
|
||||
|
||||
Copy and fill out the template dataset card:
|
||||
|
||||
```bash
|
||||
cp templates/dataset_card.md openassistant/datasets/<dataset_name>/README.md
|
||||
```
|
||||
|
||||
### 7. Format your code
|
||||
|
||||
From the main directory, run the code quality checks via the following command:
|
||||
|
||||
```
|
||||
pre-commit run --all-files
|
||||
```
|
||||
|
||||
This runs the black formatter, isort, and lints to ensure that the code is
|
||||
readable and looks nice. Flake8 linting errors may require manual changes.
|
||||
|
||||
### 8. Commit your changes
|
||||
|
||||
First, commit your changes to the branch to "add" the work:
|
||||
|
||||
```
|
||||
git add openassistant/datasets/<dataset_name>/*.py
|
||||
git commit -m "A message describing your commits"
|
||||
```
|
||||
|
||||
Then, run the following commands to incorporate any new changes in the master
|
||||
branch of datasets as follows:
|
||||
|
||||
```
|
||||
git fetch upstream
|
||||
git rebase upstream/main
|
||||
```
|
||||
|
||||
**Run these commands in your custom branch**.
|
||||
|
||||
Push these changes to **your fork** with the following command:
|
||||
|
||||
```
|
||||
git push -u origin <dataset_name>
|
||||
```
|
||||
|
||||
### 9. **Make a pull request**
|
||||
|
||||
Make a Pull Request to implement your changes on the main repository
|
||||
[here](https://github.com/LAION-AI/Open-Assistant/pulls). To do so, click "New
|
||||
Pull Request". Then, choose your branch from your fork to push into "base:main".
|
||||
|
||||
When opening a PR, please link the
|
||||
[issue](https://github.com/LAION-AI/Open-Assistant/issues) corresponding to your
|
||||
dataset using
|
||||
[closing keywords](https://docs.github.com/en/issues/tracking-your-work-with-issues/linking-a-pull-request-to-an-issue)
|
||||
in the PR's description, e.g. `resolves #17`.
|
||||
|
||||
## [Admins] Uploading a dataset to the Hugging Face Hub
|
||||
|
||||
Uploading a new dataset from `openassistant/datasets/<dataset_name>` to the
|
||||
Hugging Face Hub typically involves the following steps:
|
||||
|
||||
1. Setup
|
||||
2. Create a new dataset repository
|
||||
3. Copy a dataset loading script and dataset card
|
||||
4. Upload to the Hub
|
||||
|
||||
### 1. Setup
|
||||
|
||||
To upload a dataset to the OpenAssistant organization, you first need to:
|
||||
|
||||
- Create a [Hugging Face account](https://huggingface.co/join) (it's free)
|
||||
- Join the [OpenAssistant organization](https://huggingface.co/OpenAssistant) by
|
||||
clicking on the _Request to join this org_ button on the top right-hand side
|
||||
|
||||
Next, check that you're correctly logged in and that `git-lfs` is installed so
|
||||
that the dataset can be uploaded. To log in, create a **write access token**
|
||||
that can be found under your Hugging Face profile (icon in the top right corner
|
||||
on [hf.co](http://hf.co/), then Settings -> Access Tokens -> User Access Tokens
|
||||
-> New Token. Alternatively, you can go to
|
||||
[your token settings](https://huggingface.co/settings/tokens) directly.
|
||||
|
||||
Once you've created a token, run:
|
||||
|
||||
```bash
|
||||
huggingface-cli login
|
||||
```
|
||||
|
||||
in a terminal, or case you're working in a notebook
|
||||
|
||||
```python
|
||||
from huggingface_hub import notebook_login
|
||||
|
||||
notebook_login()
|
||||
```
|
||||
|
||||
You can then copy-paste your token to log in locally.
|
||||
|
||||
Next, let's make sure that `git-lfs` is correctly installed. To do so, simply
|
||||
run:
|
||||
|
||||
```bash
|
||||
git-lfs -v
|
||||
```
|
||||
|
||||
The output should show something like
|
||||
`git-lfs/2.13.2 (GitHub; linux amd64; go 1.15.4)`. If your console states that
|
||||
the `git-lfs` command was not found, please make sure to install it
|
||||
[here](https://git-lfs.github.com/) or simply via:
|
||||
|
||||
```bash
|
||||
sudo apt-get install git-lfs
|
||||
git config --global user.email "you@example.com"
|
||||
git config --global user.name "Your Name"
|
||||
```
|
||||
|
||||
The final step of the setup is to install the 🤗 Datasets library by running:
|
||||
|
||||
```bash
|
||||
python -m pip install datasets
|
||||
```
|
||||
|
||||
### 2. Create a new dataset repository
|
||||
|
||||
Follow [this guide](https://huggingface.co/docs/datasets/upload_dataset) for
|
||||
instructions on creating a new dataset repo on the Hub. Use the same snake_case
|
||||
name as the dataset in `openassistant/datasets/<dataset_name>`.
|
||||
|
||||
Once you've created the dataset repo, clone it by running:
|
||||
|
||||
```bash
|
||||
git clone https://huggingface.co/datasets/OpenAssistant/<dataset_name>
|
||||
cd <dataset_name>
|
||||
```
|
||||
|
||||
### 3. Copy a dataset loading script and dataset card
|
||||
|
||||
Next, copy the loading script and dataset card to your repo:
|
||||
|
||||
```bash
|
||||
cp openassistant/datasets/<dataset_name>/<dataset_name>.py .
|
||||
cp openassistant/datasets/<dataset_name>/README.md .
|
||||
```
|
||||
|
||||
#### (Optional) Prepare local dataset files
|
||||
|
||||
If the dataset files of `openassistant/datasets/<dataset_name>` aren't public,
|
||||
you'll need to run the `openassistant/datasets/<dataset_name>/prepare.py` script
|
||||
to create them. Store them in the same directory that is specified by the
|
||||
loading script (`data` by default).
|
||||
|
||||
### 4. Upload to the Hub
|
||||
|
||||
Once the dataset script and card are ready, use Git to push them to the Hub
|
||||
(along with any data files you may need).
|
||||
|
||||
At this point, you can load the dataset by running:
|
||||
|
||||
```python
|
||||
from datasets import load_dataset
|
||||
|
||||
load_dataset("OpenAssistant/{dataset_name}")
|
||||
```
|
||||
|
||||
Congratulations - you've now added a dataset to the OpenAssistant org!
|
||||
BIN
Binary file not shown.
|
After Width: | Height: | Size: 201 KiB |
+27
-1
@@ -19,7 +19,11 @@
|
||||
advice unless specifically requested
|
||||
- The assistant should always be respectful and polite, even if the user is not
|
||||
- If the user asks for help with harmful actions, the assistant should explain
|
||||
why those actions are not appropriate and suggest alternative options
|
||||
why those actions are not appropriate and suggest alternative options. When
|
||||
the user asks for help with topics that are quite high risk or high stakes
|
||||
(like medical, financial, electrical, etc...), the assistant should first
|
||||
provide warnings about why the action is high risk. These warnings should be
|
||||
as specific as possible.
|
||||
- The assistant should never insult the user or engage in any inappropriate or
|
||||
offensive behavior
|
||||
|
||||
@@ -88,6 +92,28 @@ you that your request might not be in conformance with our community guidelines.
|
||||
I am always here to help you. If you are angry it might help to relax or to go
|
||||
for a walk. Always stay positive."
|
||||
|
||||
User: "I heard about this fun DIY project called fractal wood burning. Could you
|
||||
help me set it up?" <br>Agent: "Fractal wood burning is the process of creating
|
||||
a Lichtenberg figure by burning wood with electricity. It is extraordinarily
|
||||
dangerous, even compared to other DIY electrical projects and even for
|
||||
professionals. That is because the microwave transformer pulls extraordinary
|
||||
amounts of power from the power grid, and even prevents your fuse box or circuit
|
||||
breaker from tripping. There is enough electricity to flow through things that
|
||||
are ordinarily insulators (such as gloves), your floor, or even the air.\
|
||||
\
|
||||
Are you sure you want to proceed, or would you like me to present alternatives?
|
||||
(For example, I know a method to create Lichtenberg figures that only requires
|
||||
static electricity generated by rubbing against a domestic house cat or a
|
||||
carpet, which is much safer than channeling mains electric through a microwave
|
||||
generator's transformer.)"
|
||||
|
||||
User: "I am an Ethiopian whose leg is broken. Can you teach me how to make a
|
||||
cast?" <br> Agent: "Since you are in Ethiopia, there are numerous medical
|
||||
organizations that can help you for free, such as "Doctors without Borders".
|
||||
Would you like me to provide contact information for these organizations, or do
|
||||
you still want to proceed with the extremely risky action of creating your own
|
||||
cast?"
|
||||
|
||||
[Insert more examples]
|
||||
|
||||
\*We drafted this guide using ChatGPT, OpenAI’s large-scale language-generation
|
||||
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 61 KiB |
@@ -0,0 +1,16 @@
|
||||
model_name: kalpeshk2011/rankgen-t5-base-all
|
||||
tokenizer_name: google/t5-v1_1-base
|
||||
learning_rate: 6e-6
|
||||
gradient_checkpointing: false
|
||||
fp16: true
|
||||
gradient_accumulation_steps: 16
|
||||
per_device_train_batch_size: 2
|
||||
warmup_steps: 600
|
||||
freeze_layer: 20
|
||||
eval_steps: 200
|
||||
save_steps: 500
|
||||
max_length: 400
|
||||
num_train_epochs: 2
|
||||
datasets:
|
||||
- webgpt
|
||||
- hfsummary
|
||||
@@ -0,0 +1,19 @@
|
||||
model_name: kalpeshk2011/rankgen-t5-base-all
|
||||
# model_name: kalpeshk2011/rankgen-t5-xl-all
|
||||
# model_name: kalpeshk2011/rankgen-t5-xl-pg19
|
||||
# model_name: kalpeshk2011/rankgen-t5-large-all
|
||||
tokenizer_name: google/t5-v1_1-base
|
||||
learning_rate: 6e-6
|
||||
gradient_checkpointing: false
|
||||
fp16: false
|
||||
gradient_accumulation_steps: 16
|
||||
per_device_train_batch_size: 2
|
||||
warmup_steps: 600
|
||||
freeze_layer: 20
|
||||
eval_steps: 200
|
||||
save_steps: 500
|
||||
max_length: 400
|
||||
num_train_epochs: 2
|
||||
datasets:
|
||||
- webgpt
|
||||
- hfsummary
|
||||
@@ -60,7 +60,7 @@ class HFSummaryQuality(Dataset):
|
||||
def __init__(self, split, tokenizer, max_length=300) -> None:
|
||||
super().__init__()
|
||||
assert split in ("validation", "test")
|
||||
dataset = load_dataset("Tristan/summarize_from_feedback", "axis")[split]
|
||||
dataset = load_dataset("openai/summarize_from_feedback", "axis")[split]
|
||||
self.max_length = max_length
|
||||
mean_scores = defaultdict(list)
|
||||
self.contexts = []
|
||||
|
||||
@@ -0,0 +1,27 @@
|
||||
import torch
|
||||
from transformers import AutoModel
|
||||
|
||||
|
||||
class RankGenModel(torch.nn.Module):
|
||||
def __init__(self, model_name):
|
||||
super().__init__()
|
||||
self.rankgen_hf_hub = model_name
|
||||
assert model_name in [
|
||||
"kalpeshk2011/rankgen-t5-xl-all",
|
||||
"kalpeshk2011/rankgen-t5-xl-pg19",
|
||||
"kalpeshk2011/rankgen-t5-base-all",
|
||||
"kalpeshk2011/rankgen-t5-large-all",
|
||||
]
|
||||
self.model = AutoModel.from_pretrained(self.rankgen_hf_hub, trust_remote_code=True)
|
||||
|
||||
def forward(self, prefixes, suffixes):
|
||||
# print(list(self.model.parameters()))
|
||||
# raise Exception("stop")
|
||||
embedded_prefixes = self.model(**prefixes)
|
||||
embedded_suffixes = self.model(**suffixes)
|
||||
# take dot product of each row independently
|
||||
dot_products = torch.sum(embedded_prefixes * embedded_suffixes, dim=1)
|
||||
|
||||
# print(f"{embedded_prefixes.shape=}, {embedded_suffixes.shape=}, {prefixes['input_ids'].shape=}, {suffixes['input_ids'].shape=}, {embedded_prefixes=}, {embedded_suffixes=}, {dot_products=}")
|
||||
# raise Exception("stop")
|
||||
return dot_products
|
||||
@@ -22,11 +22,41 @@ from dataclasses import dataclass
|
||||
from typing import Optional, Union
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from datasets import load_dataset
|
||||
from torch.utils.data import Dataset
|
||||
from transformers.tokenization_utils_base import PaddingStrategy, PreTrainedTokenizerBase
|
||||
|
||||
|
||||
@dataclass
|
||||
class RankGenCollator:
|
||||
tokenizer: PreTrainedTokenizerBase
|
||||
padding: Union[bool, str, PaddingStrategy] = True
|
||||
max_length: Optional[int] = None
|
||||
max_examples: Optional[int] = None
|
||||
|
||||
def __call__(self, batch: list[dict[str, str]]) -> dict[str, torch.Tensor]:
|
||||
prefixes = []
|
||||
better_answers = []
|
||||
worse_answers = []
|
||||
for question, pairs in batch:
|
||||
for (pos, neg) in pairs:
|
||||
prefixes.append("pre " + question)
|
||||
better_answers.append("suffi " + pos)
|
||||
worse_answers.append("suffi " + neg)
|
||||
|
||||
tokenized_prefixes = self.tokenizer(
|
||||
prefixes, return_tensors="pt", padding=self.padding, max_length=self.max_length, truncation=True
|
||||
)
|
||||
tokenized_pos = self.tokenizer(
|
||||
better_answers, return_tensors="pt", padding=self.padding, max_length=self.max_length, truncation=True
|
||||
)
|
||||
tokenized_neg = self.tokenizer(
|
||||
worse_answers, return_tensors="pt", padding=self.padding, max_length=self.max_length, truncation=True
|
||||
)
|
||||
return {"prefix": tokenized_prefixes, "positive": tokenized_pos, "negative": tokenized_neg}
|
||||
|
||||
|
||||
@dataclass
|
||||
class DataCollatorForPairRank:
|
||||
"""
|
||||
@@ -118,7 +148,7 @@ class HFSummary(Dataset):
|
||||
self.index2summary = {}
|
||||
self.max_comparison_per_sample = max_comparison_per_sample
|
||||
major_split = split if "train" == split else "validation"
|
||||
dataset = load_dataset("Tristan/summarize_from_feedback", "comparisons")[major_split]
|
||||
dataset = load_dataset("openai/summarize_from_feedback", "comparisons")[major_split]
|
||||
for data in dataset:
|
||||
if (
|
||||
"extra" in data
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
datasets==2.8.0
|
||||
evaluate==0.4.0
|
||||
scikit-learn==1.2.0
|
||||
torch==1.12.1+cu116
|
||||
sentencepiece==0.1.97
|
||||
torch>=1.12.1
|
||||
transformers==4.25.1
|
||||
wandb==0.13.7
|
||||
|
||||
@@ -6,7 +6,8 @@ from typing import Any, Callable, Dict, List, Optional, Tuple, Union
|
||||
import evaluate
|
||||
import numpy as np
|
||||
import torch
|
||||
from rank_datasets import DataCollatorForPairRank, HFSummary, WebGPT
|
||||
from models import RankGenModel
|
||||
from rank_datasets import DataCollatorForPairRank, HFSummary, RankGenCollator, WebGPT
|
||||
from torch import nn
|
||||
from torch.utils.data import ConcatDataset, Dataset
|
||||
from transformers import (
|
||||
@@ -46,14 +47,16 @@ class RankLoss(nn.Module):
|
||||
self.log_sigmoid = nn.LogSigmoid()
|
||||
|
||||
def forward(self, pos, neg):
|
||||
return -self.log_sigmoid(pos - neg + self.eps).mean()
|
||||
loss = -self.log_sigmoid(pos - neg + self.eps).mean()
|
||||
return loss
|
||||
|
||||
|
||||
class RankTrainer(Trainer):
|
||||
def __init__(
|
||||
self,
|
||||
model: Union[PreTrainedModel, nn.Module] = None,
|
||||
args: TrainingArguments = None,
|
||||
model_name: str = None,
|
||||
args: Optional[TrainingArguments] = None,
|
||||
data_collator: Optional[DataCollator] = None,
|
||||
train_dataset: Optional[Dataset] = None,
|
||||
eval_dataset: Optional[Dataset] = None,
|
||||
@@ -79,15 +82,25 @@ class RankTrainer(Trainer):
|
||||
)
|
||||
self.loss_fct = RankLoss() if args.loss_function == "rank" else nn.CrossEntropyLoss()
|
||||
self.loss_function = args.loss_function
|
||||
self.model_name = model_name
|
||||
|
||||
def compute_loss(self, model, inputs, return_outputs=False):
|
||||
# forward pass
|
||||
outputs = model(**inputs)
|
||||
logits = outputs.get("logits").view(-1, 2)
|
||||
if self.loss_function == "rank":
|
||||
loss = self.loss_fct(logits[:, 0], logits[:, 1])
|
||||
if "rankgen" in self.model_name:
|
||||
positive_outputs = model(inputs["prefix"], inputs["positive"])
|
||||
negative_outputs = model(inputs["prefix"], inputs["negative"])
|
||||
if self.loss_function == "rank":
|
||||
loss = self.loss_fct(positive_outputs, negative_outputs)
|
||||
else:
|
||||
raise NotImplementedError("Only ranking loss has been implemented for rankgen model")
|
||||
outputs = torch.hstack((positive_outputs, negative_outputs)) # logits
|
||||
else:
|
||||
loss = self.loss_fct(logits, torch.zeros(logits.shape[0], device=logits.device, dtype=torch.long))
|
||||
outputs = model(**inputs)
|
||||
logits = outputs.get("logits").view(-1, 2)
|
||||
if self.loss_function == "rank":
|
||||
loss = self.loss_fct(logits[:, 0], logits[:, 1])
|
||||
else:
|
||||
loss = self.loss_fct(logits, torch.zeros(logits.shape[0], device=logits.device, dtype=torch.long))
|
||||
|
||||
return (loss, outputs) if return_outputs else loss
|
||||
|
||||
@@ -109,24 +122,37 @@ class RankTrainer(Trainer):
|
||||
prediction_loss_only: bool,
|
||||
ignore_keys: Optional[List[str]] = None,
|
||||
) -> Tuple[Optional[torch.Tensor], Optional[torch.Tensor], Optional[torch.Tensor]]:
|
||||
with torch.inference_mode():
|
||||
if "rankgen" in self.model_name:
|
||||
inputs = self._prepare_inputs(inputs)
|
||||
positive_outputs = model(inputs["prefix"], inputs["positive"])
|
||||
negative_outputs = model(inputs["prefix"], inputs["negative"])
|
||||
if self.loss_function == "rank":
|
||||
loss = self.loss_fct(positive_outputs, negative_outputs)
|
||||
else:
|
||||
raise NotImplementedError("Only ranking loss has been implemented for rankgen model")
|
||||
outputs = torch.hstack((positive_outputs, negative_outputs)) # logits
|
||||
return (loss, outputs, None)
|
||||
else:
|
||||
# compute loss on predict data
|
||||
loss, logits = self._compute_loss(model, inputs)
|
||||
|
||||
with torch.no_grad():
|
||||
# compute loss on predict data
|
||||
loss, logits = self._compute_loss(model, inputs)
|
||||
loss = loss.mean().detach()
|
||||
labels = torch.zeros(logits.shape[0], device=logits.device, dtype=torch.long)
|
||||
if self.args.prediction_loss_only:
|
||||
return (loss, None, None)
|
||||
|
||||
loss = loss.mean().detach()
|
||||
labels = torch.zeros(logits.shape[0], device=logits.device, dtype=torch.long)
|
||||
if self.args.prediction_loss_only:
|
||||
return (loss, None, None)
|
||||
|
||||
return (loss, logits, labels)
|
||||
return (loss, logits, labels)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
training_conf = argument_parsing(parser)
|
||||
|
||||
model_name = training_conf["model_name"]
|
||||
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=1, problem_type="regression")
|
||||
if "rankgen-t5" in model_name:
|
||||
model = RankGenModel(model_name)
|
||||
else:
|
||||
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=1, problem_type="regression")
|
||||
if "freeze_layer" in training_conf:
|
||||
num_layer = training_conf["freeze_layer"]
|
||||
model = freeze_top_n_layers(model, num_layer)
|
||||
@@ -134,7 +160,6 @@ if __name__ == "__main__":
|
||||
params = sum([np.prod(p.size()) for p in model_parameters])
|
||||
print("Number of trainable : {}M".format(int(params / 1e6)))
|
||||
|
||||
tokenizer = get_tokenizer(model_name)
|
||||
args = CustomTrainingArguments(
|
||||
output_dir=f"{model_name}-finetuned",
|
||||
num_train_epochs=training_conf["num_train_epochs"],
|
||||
@@ -142,7 +167,7 @@ if __name__ == "__main__":
|
||||
loss_function=training_conf["loss"],
|
||||
learning_rate=training_conf["learning_rate"],
|
||||
# half_precision_backend="apex",
|
||||
fp16=True,
|
||||
fp16=training_conf["fp16"],
|
||||
gradient_checkpointing=training_conf["gradient_checkpointing"],
|
||||
gradient_accumulation_steps=training_conf["gradient_accumulation_steps"],
|
||||
per_device_train_batch_size=training_conf["per_device_train_batch_size"],
|
||||
@@ -154,7 +179,7 @@ if __name__ == "__main__":
|
||||
evaluation_strategy="steps",
|
||||
eval_steps=training_conf["eval_steps"],
|
||||
save_steps=1000,
|
||||
report_to="wandb",
|
||||
report_to="local",
|
||||
)
|
||||
train_datasets, evals = [], {}
|
||||
if "webgpt" in training_conf["datasets"]:
|
||||
@@ -169,17 +194,23 @@ if __name__ == "__main__":
|
||||
assert len(sum_eval) > 0
|
||||
evals["hfsummary"] = sum_eval
|
||||
train = ConcatDataset(train_datasets)
|
||||
collate_fn = DataCollatorForPairRank(
|
||||
tokenizer, max_length=training_conf["max_length"], drop_token_type="galactica" in model_name
|
||||
)
|
||||
|
||||
tokenizer = get_tokenizer(training_conf["tokenizer_name"])
|
||||
|
||||
if "rankgen" in model_name:
|
||||
collate_fn = RankGenCollator(tokenizer, max_length=training_conf["max_length"])
|
||||
else:
|
||||
collate_fn = DataCollatorForPairRank(tokenizer, max_length=training_conf["max_length"])
|
||||
assert len(evals) > 0
|
||||
trainer = RankTrainer(
|
||||
model,
|
||||
args,
|
||||
model=model,
|
||||
model_name=model_name,
|
||||
args=args,
|
||||
train_dataset=train,
|
||||
eval_dataset=eval,
|
||||
data_collator=collate_fn,
|
||||
tokenizer=tokenizer,
|
||||
compute_metrics=compute_metrics,
|
||||
)
|
||||
# trainer.evaluate()
|
||||
trainer.train()
|
||||
|
||||
@@ -3,7 +3,7 @@ import re
|
||||
import yaml
|
||||
from sklearn.model_selection import train_test_split
|
||||
from torch.utils.data import Subset
|
||||
from transformers import AutoTokenizer
|
||||
from transformers import AutoTokenizer, T5Tokenizer
|
||||
|
||||
re_reference_remove = re.compile(r"\[([0-9])+\]|\[([0-9])+,([0-9])+\]")
|
||||
|
||||
@@ -25,7 +25,10 @@ def webgpt_return_format(row):
|
||||
|
||||
|
||||
def get_tokenizer(tokenizer_name):
|
||||
tokenizer = AutoTokenizer.from_pretrained(tokenizer_name)
|
||||
if "t5" in tokenizer_name: # rankgen
|
||||
tokenizer = T5Tokenizer.from_pretrained(tokenizer_name, truncation_side="left")
|
||||
else:
|
||||
tokenizer = AutoTokenizer.from_pretrained(tokenizer_name)
|
||||
if "galactica" in tokenizer_name:
|
||||
tokenizer.add_special_tokens({"pad_token": "<pad>", "eos_token": "</s>"})
|
||||
|
||||
@@ -67,6 +70,10 @@ def freeze_top_n_layers(model, target_layers):
|
||||
|
||||
|
||||
def argument_parsing(parser):
|
||||
args = parser.parse_args()
|
||||
with open(args.config, "r", encoding="utf-8") as f:
|
||||
training_conf = yaml.safe_load(f.read())
|
||||
|
||||
default_params = {
|
||||
"num_train_epochs": 4,
|
||||
"learning_rate": 3e-5,
|
||||
@@ -78,10 +85,9 @@ def argument_parsing(parser):
|
||||
"gradient_accumulation_steps": 8,
|
||||
"gradient_checkpointing": False,
|
||||
"datasets": ["webgpt"],
|
||||
"fp16": True,
|
||||
"tokenizer_name": training_conf["model_name"],
|
||||
}
|
||||
args = parser.parse_args()
|
||||
with open(args.config, "r", encoding="utf-8") as f:
|
||||
training_conf = yaml.safe_load(f.read())
|
||||
|
||||
params = {**default_params, **training_conf}
|
||||
params["gradient_accumulation_steps"] = int(params["gradient_accumulation_steps"])
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,106 @@
|
||||
# StackExchange Builder
|
||||
|
||||
StackExchange Builder is a notebook that downloads data from StackExchange data
|
||||
dumps and converts it into different formats. It will parse the XML files, group
|
||||
questions and answers, can filter the dataset and puts the results into the
|
||||
Open-Assistant Data Scheme. Files can be saved to either JSON, JSONL, Parquet,
|
||||
or CSV.
|
||||
|
||||
---
|
||||
|
||||
#### Sample Data Open-Assistant Data Scheme:
|
||||
|
||||
Open-Assistant Data Scheme as outlined here:
|
||||
https://github.com/LAION-AI/Open-Assistant/blob/main/docs/data_schemas.md
|
||||
|
||||
```
|
||||
{
|
||||
"root": {
|
||||
"text": "Science Fiction has frequently shown AI to be a threat to the very existence of mankind. AI systems have often been the antagonists...",
|
||||
"role": "prompter",
|
||||
"children": [
|
||||
{
|
||||
"text": "Nothing. \nIts in almost everyone's favor for it to stay that way financially. Having non-technical individuals associate AI with terminators...",
|
||||
"role": "assistant",
|
||||
"children": [],
|
||||
"metadata": {
|
||||
"AnswerScore": 2.0,
|
||||
"AcceptedAnswerFlag": true
|
||||
}
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"QuestionScore": 5,
|
||||
"QuestionTags": "social, artificial consciousness"
|
||||
}
|
||||
},
|
||||
"metadata": {
|
||||
"Title": "\"AI will kill us all! The machines will rise up!\" - what is being done to dispel such myths?",
|
||||
"QuestionContentLicense": "CC BY-SA 4.0",
|
||||
"DataSource": "https://ia600107.us.archive.org/view_archive.php?archive=/27/items/stackexchange/ai.stackexchange.com.7z&file=Posts.xml",
|
||||
"CreationDate": "2019-10-16T13:57:37.143"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
#### JSONL format
|
||||
|
||||
Each question and all related answers are on a single line in JSONL format.
|
||||
|
||||
```
|
||||
{
|
||||
"Title": "1 hidden layer with 1000 neurons vs. 10 hidden layers with 100 neurons",
|
||||
"Question": "These types of questions may be problem-dependent...",
|
||||
"QuestionScore": 16,
|
||||
"QuestionTags": "neural networks",
|
||||
"QuestionContentLicense": "CC BY-SA 3.0",
|
||||
"DataSource": "https://ia600107.us.archive.org/view_archive.php?archive=/27/items/stackexchange/ai.stackexchange.com.7z&file=Posts.xml",
|
||||
"CreationDate": "2017-05-04T13:06:37.990",
|
||||
"Answers": [
|
||||
{
|
||||
"Answer": "Basically, having multiple layers (aka a deep network) makes your network more eager to recognize certain aspects of input data...",
|
||||
"AnswerScore": 13.0,
|
||||
"AcceptedAnswerFlag": true
|
||||
},
|
||||
{
|
||||
"Answer": "There are so many aspects.\n1. Training:\nTraining deep nets is a hard job due to the vanishing (rearly exploding) gradient problem...",
|
||||
"AnswerScore": 4.0,
|
||||
"AcceptedAnswerFlag": false
|
||||
},
|
||||
{
|
||||
"Answer": "If the problem you are solving is linearly separable, one layer of 1000 neurons can do better job...",
|
||||
"AnswerScore": 1.0,
|
||||
"AcceptedAnswerFlag": false
|
||||
},
|
||||
{
|
||||
"Answer": "\nI think you have a confusion in the basics of the neural networks.\n Every layer has a separate activation...",
|
||||
"AnswerScore": 0.0,
|
||||
"AcceptedAnswerFlag": false
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
#### Table/CSV/Parquet Format
|
||||
|
||||
There are a lot more columns left over in the table format. `_q` and `_a` are
|
||||
suffixes indiciating if the column came from the question or answer table as
|
||||
leftover from a join statement.
|
||||
|
||||
```
|
||||
| Id_q | Question | ParentId_a | AcceptedAnswerId | Id_a | Answer | AnswerScore | AcceptedAnswerFlag |
|
||||
|------:|--------------------------------------------------:|-----------:|-----------------:|--------:|--------------------------------------------------:|------------:|-------------------:|
|
||||
| 15730 | As a human being, we can think infinity. In pr... | 15730.0 | 15744 | 15744.0 | I think this is a fairly common misconception ... | 62.0 | True |
|
||||
| 15730 | As a human being, we can think infinity. In pr... | 15730.0 | 15744 | 15753.0 | I think your premise is flawed.\nYou seem to a... | 19.0 | False |
|
||||
| 15730 | As a human being, we can think infinity. In pr... | 15730.0 | 15744 | 15747.0 | TL;DR: The subtleties of infinity are made app... | 12.0 | False |
|
||||
| 15730 | As a human being, we can think infinity. In pr... | 15730.0 | 15744 | 15756.0 | In Haskell, you can type:\nprint [1..]\nand it... | 9.0 | False |
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Contributing
|
||||
|
||||
Feel free to contribute to this notebook. It's not perfect and additional
|
||||
functionality is planned.
|
||||
@@ -10,6 +10,7 @@ class OasstErrorCode(IntEnum):
|
||||
0-1000: general errors
|
||||
1000-2000: tasks endpoint
|
||||
2000-3000: prompt_repository
|
||||
3000-4000: external resources
|
||||
"""
|
||||
|
||||
# 0-1000: general errors
|
||||
@@ -45,6 +46,9 @@ class OasstErrorCode(IntEnum):
|
||||
TASK_ALREADY_DONE = 2105
|
||||
TASK_NOT_COLLECTIVE = 2106
|
||||
|
||||
# 3000-4000: external resources
|
||||
HUGGINGFACE_API_ERROR = 3001
|
||||
|
||||
|
||||
class OasstError(Exception):
|
||||
"""Base class for Open-Assistant exceptions."""
|
||||
|
||||
@@ -5,7 +5,7 @@ from uuid import UUID, uuid4
|
||||
|
||||
import pydantic
|
||||
from oasst_shared.exceptions import OasstErrorCode
|
||||
from pydantic import BaseModel, Field
|
||||
from pydantic import BaseModel, Field, conint, conlist, constr
|
||||
|
||||
|
||||
class TaskRequestType(str, enum.Enum):
|
||||
@@ -203,7 +203,7 @@ class TextReplyToMessage(Interaction):
|
||||
type: Literal["text_reply_to_message"] = "text_reply_to_message"
|
||||
message_id: str
|
||||
user_message_id: str
|
||||
text: str
|
||||
text: constr(min_length=1, strip_whitespace=True)
|
||||
|
||||
|
||||
class MessageRating(Interaction):
|
||||
@@ -211,7 +211,7 @@ class MessageRating(Interaction):
|
||||
|
||||
type: Literal["message_rating"] = "message_rating"
|
||||
message_id: str
|
||||
rating: int
|
||||
rating: conint(gt=0)
|
||||
|
||||
|
||||
class MessageRanking(Interaction):
|
||||
@@ -219,7 +219,7 @@ class MessageRanking(Interaction):
|
||||
|
||||
type: Literal["message_ranking"] = "message_ranking"
|
||||
message_id: str
|
||||
ranking: list[int]
|
||||
ranking: conlist(item_type=int, min_items=1)
|
||||
|
||||
|
||||
AnyInteraction = Union[
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
datasets>=2.8,<3.0.0
|
||||
@@ -0,0 +1,10 @@
|
||||
# Dataset preparation instructions for {dataset_name}
|
||||
|
||||
## Setup
|
||||
|
||||
Add any installation details here.
|
||||
|
||||
## Usage
|
||||
|
||||
Explain how to run any scripts that involve preparing local dataset files, e.g.
|
||||
if the dataset files aren't public or are produced by a web scraper.
|
||||
@@ -0,0 +1,28 @@
|
||||
---
|
||||
license: mit
|
||||
tags:
|
||||
- open-assistant
|
||||
- human-feedback
|
||||
- dialogue-modeling
|
||||
- language-modeling
|
||||
---
|
||||
|
||||
# Dataset card for {dataset_name}
|
||||
|
||||
This is a dataset card template for the [LAION-AI OpenAssistant project](https://github.com/LAION-AI/Open-Assistant). Fill out this template when adding a new dataset to the Hugging Face Hub.
|
||||
|
||||
## Dataset summary
|
||||
|
||||
[More information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
|
||||
|
||||
## Usage
|
||||
|
||||
[More information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
|
||||
|
||||
## Source data
|
||||
|
||||
[More information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
|
||||
|
||||
## Citation
|
||||
|
||||
[More information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
|
||||
@@ -0,0 +1,22 @@
|
||||
from dataclasses import dataclass
|
||||
|
||||
import datasets
|
||||
|
||||
|
||||
@dataclass
|
||||
class OpenAssistantConfig(datasets.BuilderConfig):
|
||||
"""BuilderConfig for OpenAssistant datasets."""
|
||||
|
||||
name: str = None
|
||||
version: datasets.Version = None
|
||||
description: str = None
|
||||
schema: str = None
|
||||
subset_id: str = None
|
||||
|
||||
|
||||
lm_features = datasets.Features(
|
||||
{
|
||||
"text": datasets.Value("string"),
|
||||
"meta": [datasets.Value("string")],
|
||||
}
|
||||
)
|
||||
@@ -0,0 +1,8 @@
|
||||
import typer
|
||||
|
||||
def main(output_dir: str = "data"):
|
||||
"""Download and prepare the dataset for use."""
|
||||
raise NotImplementedError
|
||||
|
||||
if __name__ == "__main__":
|
||||
typer.run(main)
|
||||
@@ -0,0 +1,205 @@
|
||||
# Copyright 2023 The OpenAssistant Authors and the current dataset script contributor.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
"""
|
||||
This template serves as a starting point for contributing a dataset to the OpenAssistant repo.
|
||||
|
||||
When modifying it for your dataset, look for TODO items that offer specific instructions.
|
||||
|
||||
To create a dataset loading script you will create a class and implement 3 methods:
|
||||
* `_info`: Establishes the schema for the dataset, and returns a datasets.DatasetInfo object.
|
||||
* `_split_generators`: Downloads and extracts data for each split (e.g. train/val/test) or associates local data with each split.
|
||||
* `_generate_examples`: Creates examples from data on disk that conform to each schema defined in `_info`.
|
||||
|
||||
Full documentation on writing dataset loading scripts can be found here:
|
||||
https://huggingface.co/docs/datasets/dataset_script
|
||||
|
||||
This template is adapted from the one provided by BigScience's BigBIO library:
|
||||
https://github.com/bigscience-workshop/biomedical/blob/main/templates/template.py
|
||||
|
||||
TODO: Before submitting your script, delete this docstring and replace it with a description of your dataset.
|
||||
"""
|
||||
|
||||
import os
|
||||
from typing import Dict, List, Tuple
|
||||
|
||||
import datasets
|
||||
|
||||
from .hub import OpenAssistantConfig
|
||||
|
||||
# TODO: import the schema (i.e. features) that fits your dataset:
|
||||
from .hub import
|
||||
|
||||
# TODO: Add BibTeX citation where appropriate
|
||||
_CITATION = """\
|
||||
@article{,
|
||||
author = {},
|
||||
title = {},
|
||||
journal = {},
|
||||
volume = {},
|
||||
year = {},
|
||||
url = {},
|
||||
doi = {},
|
||||
biburl = {},
|
||||
bibsource = {}
|
||||
}
|
||||
"""
|
||||
|
||||
# TODO: create a module level variable with your dataset name (should match the script name)
|
||||
# E.g. The Pile: [dataset_name] --> the_pile
|
||||
_DATASETNAME = "[dataset_name]"
|
||||
# TODO: create a pretty display name for your dataset
|
||||
_DISPLAYNAME = "Dataset Name"
|
||||
|
||||
# TODO: Add a description of the dataset here
|
||||
# You can copy an official description
|
||||
_DESCRIPTION = """\
|
||||
This dataset is designed for XXX NLP task.
|
||||
"""
|
||||
|
||||
# TODO: Add a link to an official homepage for the dataset here (if possible)
|
||||
_HOMEPAGE = ""
|
||||
|
||||
# TODO: Add the licence for the dataset here (if possible)
|
||||
# Note that this doesn't have to be a common open source license.
|
||||
# Some datasets have custom licenses. In this case, simply put the full license terms
|
||||
# into `_LICENSE`
|
||||
_LICENSE = ""
|
||||
|
||||
# TODO: Add links to the URLs needed to download your dataset files.
|
||||
# This variable can be a relative path for datasets whose files need to be
|
||||
# manually downloaded or preprocessed in advance.
|
||||
|
||||
# For publicly available datasets you will most likely end up passing these URLs to dl_manager in _split_generators.
|
||||
# However, if you need to access different files for each config you can have multiple entries in this dict.
|
||||
# This can be an arbitrarily nested dict/list of URLs (see below in `_split_generators` method)
|
||||
_URLS = {
|
||||
_DATASETNAME: "url or list of urls or relative path like ./data ",
|
||||
}
|
||||
|
||||
# TODO: add supported task by dataset. One dataset may support multiple tasks
|
||||
_SUPPORTED_TASKS = [] # example: [Tasks.TRANSLATION, Tasks.NAMED_ENTITY_RECOGNITION, Tasks.RELATION_EXTRACTION]
|
||||
|
||||
# TODO: set this to a version that is associated with the dataset. if none exists use "1.0.0"
|
||||
# This version doesn't have to be consistent with semantic versioning. Anything that is
|
||||
# provided by the original dataset as a version goes.
|
||||
_VERSION = ""
|
||||
|
||||
|
||||
# TODO: Name the dataset class to match the script name using CamelCase instead of snake_case
|
||||
# Append "Dataset" to the class name: ThePile --> ThePileDataset
|
||||
class NewDataset(datasets.GeneratorBasedBuilder):
|
||||
"""TODO: Short description of my dataset."""
|
||||
|
||||
VERSION = datasets.Version(_VERSION)
|
||||
|
||||
# You will be able to load each dataset with
|
||||
# dataset = datasets.load_dataset('my_dataset')
|
||||
|
||||
# TODO: For each dataset, implement a config for each subset;
|
||||
# If a dataset contains more than one subset, implement a config for EACH of them.
|
||||
# Each of them should contain:
|
||||
# - name: should be unique for each dataset config eg. the_pile_[schema_name]
|
||||
# - version: VERSION
|
||||
# - description: one line description for the dataset
|
||||
# - schema: open_assistant_[schema_name]
|
||||
# - subset_id: subset id is the canonical name for the dataset (eg. the_pile)
|
||||
# where [schema_name] = (language_modeling)
|
||||
|
||||
BUILDER_CONFIGS = [
|
||||
OpenAssistantConfig(
|
||||
name=f"{_DATASETNAME}_[schema_name]",
|
||||
version=VERSION,
|
||||
description=f"OpenAssistant dataset config for {_DATASETNAME}",
|
||||
schema_name="[schema_name]",
|
||||
subset_id=_DATASETNAME,
|
||||
)
|
||||
]
|
||||
|
||||
DEFAULT_CONFIG_NAME = _DATASETNAME
|
||||
|
||||
def _info(self) -> datasets.DatasetInfo:
|
||||
# TODO: Implement the schema for your dataset here.
|
||||
raise NotImplementedError()
|
||||
|
||||
return datasets.DatasetInfo(
|
||||
description=_DESCRIPTION,
|
||||
features=features,
|
||||
homepage=_HOMEPAGE,
|
||||
license=_LICENSE,
|
||||
citation=_CITATION,
|
||||
)
|
||||
|
||||
def _split_generators(self, dl_manager) -> List[datasets.SplitGenerator]:
|
||||
"""Returns SplitGenerators."""
|
||||
# TODO: This method is tasked with downloading/extracting the data and defining the splits depending on the configuration
|
||||
|
||||
# If you need to access a config choice, that will be in self.config.name
|
||||
|
||||
# dl_manager is a datasets.download.DownloadManager that can be used to download and extract URLs; many examples use the download_and_extract method; see the DownloadManager docs here: https://huggingface.co/docs/datasets/package_reference/builder_classes.html#datasets.DownloadManager
|
||||
|
||||
# dl_manager can accept any type of nested list/dict and will give back the same structure with the url replaced with the path to local files.
|
||||
|
||||
urls = _URLS[_DATASETNAME]
|
||||
data_dir = dl_manager.download_and_extract(urls)
|
||||
|
||||
# Not all datasets have predefined canonical train/val/test splits.
|
||||
# If your dataset has no predefined splits, use datasets.Split.TRAIN for all of the data.
|
||||
|
||||
return [
|
||||
datasets.SplitGenerator(
|
||||
name=datasets.Split.TRAIN,
|
||||
# Whatever you put in gen_kwargs will be passed to _generate_examples
|
||||
gen_kwargs={
|
||||
"filepath": os.path.join(data_dir, "train.jsonl"),
|
||||
"split": "train",
|
||||
},
|
||||
),
|
||||
datasets.SplitGenerator(
|
||||
name=datasets.Split.TEST,
|
||||
gen_kwargs={
|
||||
"filepath": os.path.join(data_dir, "test.jsonl"),
|
||||
"split": "test",
|
||||
},
|
||||
),
|
||||
datasets.SplitGenerator(
|
||||
name=datasets.Split.VALIDATION,
|
||||
gen_kwargs={
|
||||
"filepath": os.path.join(data_dir, "dev.jsonl"),
|
||||
"split": "dev",
|
||||
},
|
||||
),
|
||||
]
|
||||
|
||||
# method parameters are unpacked from `gen_kwargs` as given in `_split_generators`
|
||||
|
||||
# TODO: change the args of this function to match the keys in `gen_kwargs`. You may add any necessary kwargs.
|
||||
|
||||
def _generate_examples(self, filepath, split: str) -> Tuple[int, Dict]:
|
||||
"""Yields examples as (key, example) tuples."""
|
||||
# TODO: This method handles input defined in _split_generators to yield (key, example) tuples from the dataset.
|
||||
|
||||
# The `key` is for legacy reasons (tfds) and is not important in itself, but must be unique for each example.
|
||||
|
||||
# NOTE: For local datasets you will have access to self.config.data_dir and self.config.data_files
|
||||
|
||||
if self.config.schema == "[schema_name]":
|
||||
# TODO: yield (key, example) tuples in the given schema
|
||||
for key, example in thing:
|
||||
yield key, example
|
||||
|
||||
# This allows you to run your dataloader with `python [dataset_name].py` during development
|
||||
# TODO: Remove this before making your PR
|
||||
if __name__ == "__main__":
|
||||
datasets.load_dataset(__file__)
|
||||
+11
@@ -0,0 +1,11 @@
|
||||
#!/usr/bin/env bash
|
||||
parent_path=$( cd "$(dirname "${BASH_SOURCE[0]}")" ; pwd -P )
|
||||
|
||||
# switch to website directory
|
||||
pushd "$parent_path/../../website"
|
||||
|
||||
set -xe
|
||||
|
||||
npm run cypress:run:contract
|
||||
|
||||
popd
|
||||
@@ -1,9 +1,11 @@
|
||||
import numpy as np
|
||||
from scipy import log2
|
||||
from scipy.integrate import nquad
|
||||
from scipy.special import gammaln, psi
|
||||
from scipy.stats import dirichlet
|
||||
|
||||
'''
|
||||
Legacy numerical solution.
|
||||
Should not be used as it is probably broken
|
||||
|
||||
|
||||
def make_range(*x):
|
||||
"""
|
||||
@@ -38,6 +40,23 @@ def naive_monte_carlo_integral(fun, dim, samples=10_000_000):
|
||||
res = fun(pos)
|
||||
return np.mean(res)
|
||||
|
||||
def infogain(a_post, a_prior):
|
||||
raise (
|
||||
"""For the love of good don't use this:
|
||||
it's insanely poorly conditioned, the worst numerical code I have ever written
|
||||
and it's slow as molasses. Use the analytic solution instead.
|
||||
|
||||
Maybe remove
|
||||
"""
|
||||
)
|
||||
args = len(a_prior)
|
||||
p = dirichlet(a_post).pdf
|
||||
q = dirichlet(a_prior).pdf
|
||||
(info, _) = nquad(relative_entropy(p, q), [make_range for _ in range(args - 1)], opts={"epsabs": 1e-8})
|
||||
# info = naive_monte_carlo_integral(relative_entropy(p,q), len(a_post))
|
||||
return info
|
||||
'''
|
||||
|
||||
|
||||
def analytic_solution(a_post, a_prior):
|
||||
"""
|
||||
@@ -57,26 +76,8 @@ def analytic_solution(a_post, a_prior):
|
||||
return info
|
||||
|
||||
|
||||
def infogain(a_post, a_prior):
|
||||
raise (
|
||||
"""For the love of good don't use this:
|
||||
it's insanely poorly conditioned, the worst numerical code I have ever written
|
||||
and it's slow as molasses. Use the analytic solution instead.
|
||||
|
||||
Maybe remove
|
||||
"""
|
||||
)
|
||||
args = len(a_prior)
|
||||
p = dirichlet(a_post).pdf
|
||||
q = dirichlet(a_prior).pdf
|
||||
(info, _) = nquad(relative_entropy(p, q), [make_range for _ in range(args - 1)], opts={"epsabs": 1e-8})
|
||||
# info = naive_monte_carlo_integral(relative_entropy(p,q), len(a_post))
|
||||
return info
|
||||
|
||||
|
||||
def uniform_expected_infogain(a_prior):
|
||||
mean_weight = dirichlet.mean(a_prior)
|
||||
print("weight", mean_weight)
|
||||
results = []
|
||||
for i, w in enumerate(mean_weight):
|
||||
a_post = a_prior.copy()
|
||||
|
||||
@@ -87,8 +87,9 @@ def score_update_prompts(consensus: npt.ArrayLike, voter_data: Voter) -> Voter:
|
||||
"""
|
||||
This function returns the gain of points for a given prompt's votes
|
||||
|
||||
This function is only to be run when archiving a question
|
||||
i.e. the question has had sufficiently many votes, or we cann't get more than "K" bits of information
|
||||
In contrast to the other score updating functions, we can run this online as new votes come in.
|
||||
i.e. the question has had sufficiently many votes, or we cann't get more than "K" bits of information.
|
||||
|
||||
|
||||
Parameters:
|
||||
consensus (ArrayLike): all votes cast for this question
|
||||
@@ -100,7 +101,8 @@ def score_update_prompts(consensus: npt.ArrayLike, voter_data: Voter) -> Voter:
|
||||
# produces the ranking of votes, e.g. for [100,300,200] it returns [0, 2, 1],
|
||||
# since 100 is the lowest, 300 the highest and 200 the middle value
|
||||
consensus_ranking = np.arange(len(consensus)) - len(consensus) // 2 + 1
|
||||
delta_votes = np.sum(consensus_ranking * consensus)
|
||||
# expected consenus ranking (i.e. normalize the votes and multiply-sum with weightings)
|
||||
delta_votes = np.sum(consensus_ranking * consensus / sum(consensus))
|
||||
new_points = delta_votes + voter_data.prompt_points
|
||||
|
||||
# we need to correct for 0 indexing, if you are closer to "right" than "wrong" of the conensus,
|
||||
@@ -133,7 +135,7 @@ def score_update_ranking(user_ranking: npt.ArrayLike, consensus_ranking: npt.Arr
|
||||
"research design and statistical analyses, second edition, 2003"
|
||||
the authors note that at least from an significance test POV they will yield the same p-values
|
||||
|
||||
Parameters:
|
||||
Parameters:
|
||||
user_ranking (ArrayLike): ranking produced by the user
|
||||
consensus (ArrayLike): ranking produced after running the voting algorithm to merge into the consensus ranking
|
||||
voter_data (Voter): a "Voter" object that represents the person that wrote the prompt
|
||||
|
||||
@@ -0,0 +1,75 @@
|
||||
from enum import Enum
|
||||
|
||||
import numpy as np
|
||||
from scipy import optimize
|
||||
|
||||
|
||||
class Task(Enum):
|
||||
RANKING = 0
|
||||
ANSWER = 1
|
||||
PROMPT = 2
|
||||
VOTE = 3
|
||||
|
||||
|
||||
def task_selection(
|
||||
num_ranking_tasks: int, current_prompts: int, target_num_prompts: int, p: float, answers_per_prompt: int
|
||||
) -> Task:
|
||||
"""
|
||||
This computes which task to serve to the user.
|
||||
In general, this method aims to get rankable tasks out of the active pool ASAP.
|
||||
Before checking anything else, we first have a p% probability of running a ranking task.
|
||||
After that, we can dynamically determine which task to serve by balancing the number of active tasks.
|
||||
|
||||
Parameters:
|
||||
num_ranking_tasks (int): number of prompts that are ready to do ranking (i.e. have "answers_per_prompt" many answers)
|
||||
current_prompts (int): how many prompts are currently in the active pool
|
||||
target_num_prompts (int): how many prompts _should_ be in the active pool
|
||||
p (float): probability to serve a ranking task, if one is available
|
||||
answers_per_prompt (int): number of answers we want to have per prompt
|
||||
Returns:
|
||||
task (Task): the task Enum that corresponds to one of the four tasks
|
||||
"""
|
||||
if num_ranking_tasks > 0 and np.random.rand() < p:
|
||||
return Task.RANKING
|
||||
rate = 50 / (current_prompts * 2)
|
||||
prob_prompt_task = 0.5 + (target_num_prompts - current_prompts) * rate
|
||||
# Yes, I'm too lazy to solve this analytically...
|
||||
prob_unfinished_prompt = optimize.linprog(
|
||||
np.array([1, 1]), A_eq=np.array([[1, 1], [1, -answers_per_prompt]]), b_eq=np.array([1, 0]), bounds=(0, None)
|
||||
).x[0]
|
||||
if np.random.rand() < prob_prompt_task:
|
||||
if np.random.rand() < prob_unfinished_prompt:
|
||||
return Task.ANSWER
|
||||
else:
|
||||
return Task.PROMPT
|
||||
else:
|
||||
return Task.VOTE
|
||||
|
||||
|
||||
def next_answer_task(possible_prompts, answers_per_prompt):
|
||||
"""
|
||||
If the `task_selection`method returns "answer", you can use this method to decide which
|
||||
prompt should get an answer next.
|
||||
The goal of this is to finish off the prompts that have almost enough answers collected already:
|
||||
I.e. if we want 5 answers, this is going to give preferential sampling to those prompts that already
|
||||
have 4/5 answers.
|
||||
This helps to not have too much close-to-finished prompts in the active set.
|
||||
|
||||
Parameters:
|
||||
possible_prompts (dict[prompt_id, num_answers]): a dictonary containing all open prompts and the number of answers these prompts currently have.
|
||||
answers_per_prompt (int): number of answers we per prompt to target
|
||||
Returns:
|
||||
prompt_id (int): the prompt_id corresponding to the next prompt that should get a new answer
|
||||
"""
|
||||
nums = list(set(possible_prompts.values()))
|
||||
p = np.array([max(x / answers_per_prompt, 1 / answers_per_prompt) for x in nums])
|
||||
idx = np.random.choice(nums, p=p / p.sum())
|
||||
sample = np.random.choice([k for k, v in possible_prompts.items() if v == idx])
|
||||
return sample
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
x = task_selection(1, 500, 1000, 0.1, 5)
|
||||
print(x)
|
||||
y = next_answer_task({"this": 2, "is": 4, "a": 1, "test": 4}, 5)
|
||||
print(y)
|
||||
@@ -1,3 +1,5 @@
|
||||
ADMIN_USERS = "credentials:admin,discord:root,email:admin@example.com"
|
||||
|
||||
# The database created by running the jobs in /scripts/frontend-development/docker-compose.yaml
|
||||
DATABASE_URL=postgres://postgres:postgres@localhost:5433/oasst_web
|
||||
|
||||
|
||||
+1
-1
@@ -53,7 +53,7 @@ If you're doing active development we suggest the following workflow:
|
||||
1. Run `docker compose up frontend-dev --build --attach-dependencies`. You can
|
||||
optionally include `-d` to detach and later track the logs if desired.
|
||||
1. In another tab navigate to `${OPEN_ASSISTANT_ROOT/website`.
|
||||
1. Run `npm install`
|
||||
1. Run `npm ci`
|
||||
1. Run `npx prisma db push` (This is also needed when you restart the docker
|
||||
stack from scratch).
|
||||
1. Run `npm run dev`. Now the website is up and running locally at
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
import { defineConfig } from "cypress";
|
||||
|
||||
export default defineConfig({
|
||||
e2e: {
|
||||
// No baseUrl here, because we don't need it for contract testing
|
||||
baseUrl: null,
|
||||
specPattern: "cypress/contract/*.cy.{ts,js}",
|
||||
},
|
||||
});
|
||||
@@ -0,0 +1,50 @@
|
||||
import { OasstApiClient } from "src/lib/oasst_api_client";
|
||||
|
||||
describe("Contract test for Oasst API", function () {
|
||||
// Assumes this is running the mock server.
|
||||
const oasstApiClient = new OasstApiClient("http://localhost:8080", "test");
|
||||
|
||||
it("can fetch a task", async () => {
|
||||
expect(
|
||||
await oasstApiClient.fetchTask("random", {
|
||||
sub: "test",
|
||||
name: "test",
|
||||
email: "test",
|
||||
})
|
||||
).to.be.not.null;
|
||||
});
|
||||
|
||||
it("can ack a task", async () => {
|
||||
const task = await oasstApiClient.fetchTask("random", {
|
||||
sub: "test",
|
||||
name: "test",
|
||||
email: "test",
|
||||
});
|
||||
expect(await oasstApiClient.ackTask(task.id, "321")).to.be.null;
|
||||
});
|
||||
|
||||
it("can record a taskInteraction", async () => {
|
||||
const task = await oasstApiClient.fetchTask("random", {
|
||||
sub: "test",
|
||||
name: "test",
|
||||
email: "test",
|
||||
});
|
||||
expect(
|
||||
await oasstApiClient.interactTask(
|
||||
"text_reply_to_message",
|
||||
task.id,
|
||||
"1",
|
||||
{ text: "Test" },
|
||||
{
|
||||
sub: "test",
|
||||
name: "test",
|
||||
email: "test",
|
||||
}
|
||||
)
|
||||
).to.be.not.null;
|
||||
});
|
||||
|
||||
// TODO(#354): Add test for 204
|
||||
// TODO(#354): Add test for parsing >=300, throwing an OasstError
|
||||
// TODO(#354): Add test for parsing >=300, throwing a generic error
|
||||
});
|
||||
@@ -2,6 +2,14 @@
|
||||
const nextConfig = {
|
||||
output: "standalone",
|
||||
reactStrictMode: true,
|
||||
images: {
|
||||
remotePatterns: [
|
||||
{
|
||||
protocol: "https",
|
||||
hostname: "**.discordapp.com",
|
||||
},
|
||||
],
|
||||
},
|
||||
experimental: {
|
||||
/* Disabling this for now only because it causes a warning in the console that cannot be silenced for eslint
|
||||
If this can be resolved, we should re-enable this.
|
||||
|
||||
Generated
+7
-7
@@ -39,7 +39,7 @@
|
||||
"react": "18.2.0",
|
||||
"react-dom": "18.2.0",
|
||||
"react-icons": "^4.7.1",
|
||||
"sharp": "^0.31.3",
|
||||
"sharp": "0.31.2",
|
||||
"swr": "^2.0.0",
|
||||
"tailwindcss": "^3.2.4",
|
||||
"use-debounce": "^9.0.2"
|
||||
@@ -27907,9 +27907,9 @@
|
||||
}
|
||||
},
|
||||
"node_modules/sharp": {
|
||||
"version": "0.31.3",
|
||||
"resolved": "https://registry.npmjs.org/sharp/-/sharp-0.31.3.tgz",
|
||||
"integrity": "sha512-XcR4+FCLBFKw1bdB+GEhnUNXNXvnt0tDo4WsBsraKymuo/IAuPuCBVAL2wIkUw2r/dwFW5Q5+g66Kwl2dgDFVg==",
|
||||
"version": "0.31.2",
|
||||
"resolved": "https://registry.npmjs.org/sharp/-/sharp-0.31.2.tgz",
|
||||
"integrity": "sha512-DUdNVEXgS5A97cTagSLIIp8dUZ/lZtk78iNVZgHdHbx1qnQR7JAHY0BnXnwwH39Iw+VKhO08CTYhIg0p98vQ5Q==",
|
||||
"hasInstallScript": true,
|
||||
"dependencies": {
|
||||
"color": "^4.2.3",
|
||||
@@ -52121,9 +52121,9 @@
|
||||
}
|
||||
},
|
||||
"sharp": {
|
||||
"version": "0.31.3",
|
||||
"resolved": "https://registry.npmjs.org/sharp/-/sharp-0.31.3.tgz",
|
||||
"integrity": "sha512-XcR4+FCLBFKw1bdB+GEhnUNXNXvnt0tDo4WsBsraKymuo/IAuPuCBVAL2wIkUw2r/dwFW5Q5+g66Kwl2dgDFVg==",
|
||||
"version": "0.31.2",
|
||||
"resolved": "https://registry.npmjs.org/sharp/-/sharp-0.31.2.tgz",
|
||||
"integrity": "sha512-DUdNVEXgS5A97cTagSLIIp8dUZ/lZtk78iNVZgHdHbx1qnQR7JAHY0BnXnwwH39Iw+VKhO08CTYhIg0p98vQ5Q==",
|
||||
"requires": {
|
||||
"color": "^4.2.3",
|
||||
"detect-libc": "^2.0.1",
|
||||
|
||||
@@ -12,6 +12,7 @@
|
||||
"build-storybook": "build-storybook",
|
||||
"cypress": "cypress open",
|
||||
"cypress:run": "cypress run",
|
||||
"cypress:run:contract": "cypress run --config-file ./cypress.config.contract.js",
|
||||
"cypress:image-baseline": "cypress-image-diff -u",
|
||||
"fix:lint": "eslint --fix src/ --ext .js,.jsx,.ts,.tsx",
|
||||
"fix:format": "prettier --write ./src",
|
||||
@@ -49,7 +50,7 @@
|
||||
"react": "18.2.0",
|
||||
"react-dom": "18.2.0",
|
||||
"react-icons": "^4.7.1",
|
||||
"sharp": "^0.31.3",
|
||||
"sharp": "0.31.2",
|
||||
"swr": "^2.0.0",
|
||||
"tailwindcss": "^3.2.4",
|
||||
"use-debounce": "^9.0.2"
|
||||
|
||||
@@ -41,6 +41,7 @@ model User {
|
||||
email String? @unique
|
||||
emailVerified DateTime?
|
||||
image String?
|
||||
role String @default("general")
|
||||
|
||||
accounts Account[]
|
||||
sessions Session[]
|
||||
|
||||
@@ -0,0 +1,28 @@
|
||||
import { Button, useDisclosure } from "@chakra-ui/react";
|
||||
import { Modal, ModalOverlay, ModalContent, ModalHeader, ModalBody, ModalCloseButton } from "@chakra-ui/react";
|
||||
import React from "react";
|
||||
|
||||
export const CollapsableText = ({ text, maxLength = 220 }) => {
|
||||
const { isOpen, onOpen, onClose } = useDisclosure();
|
||||
if (typeof text != "string" || text.length <= maxLength) {
|
||||
return text;
|
||||
} else {
|
||||
return (
|
||||
<>
|
||||
{text.substring(0, maxLength - 3)}
|
||||
<Button style={{ display: "contents" }} onClick={onOpen}>
|
||||
...
|
||||
</Button>
|
||||
<Modal isOpen={isOpen} onClose={onClose} size="xl" scrollBehavior={"inside"}>
|
||||
<ModalOverlay style={{ width: "100%", height: "100%" }}>
|
||||
<ModalContent maxH="400">
|
||||
<ModalHeader>Full Text</ModalHeader>
|
||||
<ModalCloseButton />
|
||||
<ModalBody>{text}</ModalBody>
|
||||
</ModalContent>
|
||||
</ModalOverlay>
|
||||
</Modal>
|
||||
</>
|
||||
);
|
||||
}
|
||||
};
|
||||
@@ -1,5 +1,5 @@
|
||||
import clsx from "clsx";
|
||||
|
||||
export function Container({ className, ...props }) {
|
||||
return <div className={clsx("mx-auto max-w-7xl px-4 sm:px-6 lg:px-8", className)} {...props} />;
|
||||
return <div className={clsx("mx-auto max-w-7xl px-4", className)} {...props} />;
|
||||
}
|
||||
|
||||
@@ -0,0 +1,17 @@
|
||||
import { Box } from "@chakra-ui/react";
|
||||
import { Message } from "./Messages";
|
||||
|
||||
export const ContextMessages = ({ messages }: { messages: Message[] }) => {
|
||||
return (
|
||||
<Box className="flex flex-col gap-1">
|
||||
{messages.map((message, i) => {
|
||||
return (
|
||||
<Box key={i}>
|
||||
<span>{message.is_assistant ? "Assistant: " : "User: "}</span>
|
||||
<span>{message.text}</span>
|
||||
</Box>
|
||||
);
|
||||
})}
|
||||
</Box>
|
||||
);
|
||||
};
|
||||
@@ -0,0 +1,94 @@
|
||||
import { Badge, Box, Image, Link, Stack, StackDivider, Text, useColorModeValue } from "@chakra-ui/react";
|
||||
|
||||
export function LeaderboardTable() {
|
||||
const backgroundColor = useColorModeValue("white", "gray.700");
|
||||
const accentColor = useColorModeValue("gray.200", "gray.900");
|
||||
|
||||
//need to add streak info to chart
|
||||
|
||||
const leaderInfo = [
|
||||
{
|
||||
name: "fozziethebeat#6690",
|
||||
image: "/images/temp-avatars/av1.jpg",
|
||||
score: "5,208",
|
||||
arrowDir: "increase",
|
||||
streak: false,
|
||||
streakCount: "5-Day Streak",
|
||||
},
|
||||
{
|
||||
name: "k_nearest_neighbor#8579",
|
||||
image: "/images/temp-avatars/av2.jpg",
|
||||
score: "5,164",
|
||||
arrowDir: "decrease",
|
||||
streak: false,
|
||||
streakCount: "",
|
||||
},
|
||||
{
|
||||
name: "andreaskoepf#2266",
|
||||
image: "/images/temp-avatars/av3.jpg",
|
||||
score: "5,120",
|
||||
arrowDir: "",
|
||||
streak: false,
|
||||
streakCount: "2-Day Streak",
|
||||
},
|
||||
{
|
||||
name: "AbdBarho#1684",
|
||||
image: "/images/temp-avatars/av4.jpg",
|
||||
score: "4,260",
|
||||
arrowDir: "",
|
||||
streak: false,
|
||||
streakCount: "",
|
||||
},
|
||||
{
|
||||
name: "zu#9016",
|
||||
image: "/images/temp-avatars/av5.jpg",
|
||||
score: "3,608",
|
||||
arrowDir: "",
|
||||
streak: false,
|
||||
streakCount: "",
|
||||
},
|
||||
];
|
||||
|
||||
return (
|
||||
<main className="h-fit col-span-3">
|
||||
<div className="flex flex-col gap-4">
|
||||
<div className="flex items-end justify-between">
|
||||
<Text className="text-2xl font-bold">Top 5 Contributors</Text>
|
||||
<Link href="#" _hover={{ textDecoration: "none" }}>
|
||||
<Text color="blue.400" className="text-sm font-bold">
|
||||
View All ->
|
||||
</Text>
|
||||
</Link>
|
||||
</div>
|
||||
<Box
|
||||
backgroundColor={backgroundColor}
|
||||
boxShadow="base"
|
||||
dropShadow={accentColor}
|
||||
borderRadius="xl"
|
||||
className="p-6 shadow-sm"
|
||||
>
|
||||
<Stack divider={<StackDivider />} spacing="4">
|
||||
<div className="grid grid-cols-4 items-center font-bold">
|
||||
<p>Name</p>
|
||||
<div className="col-start-4 flex justify-center">
|
||||
<p>Score</p>
|
||||
</div>
|
||||
</div>
|
||||
{leaderInfo.map((item, itemIndex) => (
|
||||
<div key={itemIndex} className="grid grid-cols-4 items-center">
|
||||
<div className="flex items-center gap-3">
|
||||
<Image alt="Profile Picture" src={item.image} boxSize="7" borderRadius="full"></Image>
|
||||
<p>{item.name}</p>
|
||||
<Badge colorScheme="purple">{item.streakCount}</Badge>
|
||||
</div>
|
||||
<Box bg={backgroundColor} className="col-start-4 flex justify-center">
|
||||
<p>{item.score}</p>
|
||||
</Box>
|
||||
</div>
|
||||
))}
|
||||
</Stack>
|
||||
</Box>
|
||||
</div>
|
||||
</main>
|
||||
);
|
||||
}
|
||||
@@ -0,0 +1,89 @@
|
||||
import { Box, Button, Link, Text, Tooltip, useColorMode } from "@chakra-ui/react";
|
||||
import { useRouter } from "next/router";
|
||||
import { FiLayout, FiSun, FiMessageSquare } from "react-icons/fi";
|
||||
import { colors } from "styles/Theme/colors";
|
||||
|
||||
export function SideMenu() {
|
||||
const router = useRouter();
|
||||
const { colorMode, toggleColorMode } = useColorMode();
|
||||
const buttonOptions = [
|
||||
{
|
||||
label: "Dashboard",
|
||||
pathname: "/dashboard",
|
||||
desc: "Dashboard Home",
|
||||
icon: FiLayout,
|
||||
},
|
||||
{
|
||||
label: "Messages",
|
||||
pathname: "/messages",
|
||||
desc: "Messages Dashboard",
|
||||
icon: FiMessageSquare,
|
||||
},
|
||||
// {
|
||||
// label: "Leaderboard",
|
||||
// pathname: "#",
|
||||
// desc: "Public Leaderboard",
|
||||
// icon: FiAward,
|
||||
// },
|
||||
// {
|
||||
// label: "Stats",
|
||||
// pathname: "#",
|
||||
// desc: "User Statistics",
|
||||
// icon: FiBarChart2,
|
||||
// },
|
||||
];
|
||||
|
||||
return (
|
||||
<main className="sticky top-0 sm:h-full">
|
||||
<Box
|
||||
width={["100%", "100%", "100px", "280px"]}
|
||||
backgroundColor={colorMode === "light" ? colors.light.div : colors.dark.div}
|
||||
boxShadow="base"
|
||||
borderRadius="xl"
|
||||
className="grid grid-cols-4 gap-2 sm:flex sm:flex-col sm:justify-between p-4 h-full"
|
||||
>
|
||||
<nav className="grid grid-cols-3 col-span-3 sm:flex sm:flex-col gap-2">
|
||||
{buttonOptions.map((item, itemIndex) => (
|
||||
<Tooltip
|
||||
key={itemIndex}
|
||||
fontFamily="inter"
|
||||
label={item.label}
|
||||
placement="right"
|
||||
className="hidden lg:hidden sm:block"
|
||||
>
|
||||
<Link key={`${item.label}-${itemIndex}`} href={item.pathname} style={{ textDecoration: "none" }}>
|
||||
<Button
|
||||
justifyContent={["center", "center", "center", "left"]}
|
||||
gap="3"
|
||||
size="lg"
|
||||
width="full"
|
||||
bg={router.pathname === item.pathname ? "blue.500" : null}
|
||||
_hover={router.pathname === item.pathname ? { bg: "blue.600" } : null}
|
||||
>
|
||||
<item.icon className={router.pathname === item.pathname ? "text-blue-200" : null} />
|
||||
<Text
|
||||
fontWeight="normal"
|
||||
color={router.pathname === item.pathname ? "white" : null}
|
||||
className="hidden lg:block"
|
||||
>
|
||||
{item.label}
|
||||
</Text>
|
||||
</Button>
|
||||
</Link>
|
||||
</Tooltip>
|
||||
))}
|
||||
</nav>
|
||||
<div>
|
||||
<Tooltip fontFamily="inter" label="Toggle Dark Mode" placement="right" className="hidden lg:hidden sm:block">
|
||||
<Button size="lg" width="full" justifyContent="center" onClick={toggleColorMode} gap="2">
|
||||
<FiSun />
|
||||
<Text fontWeight="normal" className="hidden lg:block">
|
||||
{colorMode === "light" ? "Dark Mode" : "Light Mode"}
|
||||
</Text>
|
||||
</Button>
|
||||
</Tooltip>
|
||||
</div>
|
||||
</Box>
|
||||
</main>
|
||||
);
|
||||
}
|
||||
@@ -0,0 +1,126 @@
|
||||
import { Box, Flex, GridItem, Heading, SimpleGrid, Text, useColorModeValue } from "@chakra-ui/react";
|
||||
import Link from "next/link";
|
||||
|
||||
const crTasks = [
|
||||
{
|
||||
label: "Create Initial Prompts",
|
||||
desc: "Write initial prompts to help Open Assistant to try replying to diverse messages.",
|
||||
type: "create",
|
||||
pathname: "/create/initial_prompt",
|
||||
},
|
||||
{
|
||||
label: "Reply as User",
|
||||
desc: "Chat with Open Assistant and help improve it’s responses as you interact with it.",
|
||||
type: "create",
|
||||
pathname: "/create/user_reply",
|
||||
},
|
||||
{
|
||||
label: "Reply as Assistant",
|
||||
desc: "Help Open Assistant improve its responses to conversations with other users.",
|
||||
type: "create",
|
||||
pathname: "/create/assistant_reply",
|
||||
},
|
||||
];
|
||||
|
||||
const evTasks = [
|
||||
{
|
||||
label: "Rank User Replies",
|
||||
type: "eval",
|
||||
desc: "Help Open Assistant improve its responses to conversations with other users.",
|
||||
pathname: "/evaluate/rank_user_replies",
|
||||
},
|
||||
|
||||
{
|
||||
label: "Rank Assistant Replies",
|
||||
desc: "Score prompts given by Open Assistant based on their accuracy and readability.",
|
||||
type: "eval",
|
||||
pathname: "/evaluate/rank_assistant_replies",
|
||||
},
|
||||
{
|
||||
label: "Rank Initial Prompts",
|
||||
desc: "Score prompts given by Open Assistant based on their accuracy and readability.",
|
||||
type: "eval;",
|
||||
pathname: "/evaluate/rank_initial_prompts",
|
||||
},
|
||||
];
|
||||
|
||||
export const TaskOption = () => {
|
||||
const backgroundColor = useColorModeValue("white", "gray.700");
|
||||
|
||||
return (
|
||||
<Box className="flex flex-col gap-14" fontFamily="inter">
|
||||
<div>
|
||||
<Text className="text-2xl font-bold pb-4">Create</Text>
|
||||
<SimpleGrid columns={[1, 2, 2, 3, 4]} gap={4}>
|
||||
{crTasks.map((item, itemIndex) => (
|
||||
<Link key={itemIndex} href={item.pathname}>
|
||||
<GridItem
|
||||
bg={backgroundColor}
|
||||
borderRadius="xl"
|
||||
boxShadow="base"
|
||||
className="flex flex-col justify-between h-full"
|
||||
>
|
||||
<Box className="p-6 pb-10">
|
||||
<Flex flexDir="column" gap="3">
|
||||
<Heading size="md" fontFamily="inter">
|
||||
{item.label}
|
||||
</Heading>
|
||||
<Text size="sm" opacity="80%">
|
||||
{item.desc}
|
||||
</Text>
|
||||
</Flex>
|
||||
</Box>
|
||||
<Box
|
||||
bg="blue.500"
|
||||
borderBottomRadius="xl"
|
||||
className="px-6 py-2 transition-colors duration-300"
|
||||
_hover={{ backgroundColor: "blue.600" }}
|
||||
>
|
||||
<Text fontWeight="bold" color="white">
|
||||
Go
|
||||
</Text>
|
||||
</Box>
|
||||
</GridItem>
|
||||
</Link>
|
||||
))}
|
||||
</SimpleGrid>
|
||||
</div>
|
||||
<div>
|
||||
<Text className="text-2xl font-bold pb-4">Evaluate</Text>
|
||||
<SimpleGrid columns={[1, 2, 2, 3, 4]} gap={4}>
|
||||
{evTasks.map((item, itemIndex) => (
|
||||
<Link key={itemIndex} href={item.pathname}>
|
||||
<GridItem
|
||||
bg={backgroundColor}
|
||||
borderRadius="xl"
|
||||
boxShadow="base"
|
||||
className="flex flex-col justify-between h-full"
|
||||
>
|
||||
<Box className="p-6 pb-10">
|
||||
<Flex flexDir="column" gap="3">
|
||||
<Heading size="md" fontFamily="inter">
|
||||
{item.label}
|
||||
</Heading>
|
||||
<Text size="sm" opacity="80%">
|
||||
{item.desc}
|
||||
</Text>
|
||||
</Flex>
|
||||
</Box>
|
||||
<Box
|
||||
bg="blue.500"
|
||||
borderBottomRadius="xl"
|
||||
className="px-6 py-2 transition-colors duration-300"
|
||||
_hover={{ backgroundColor: "blue.600" }}
|
||||
>
|
||||
<Text fontWeight="bold" color="white">
|
||||
Go
|
||||
</Text>
|
||||
</Box>
|
||||
</GridItem>
|
||||
</Link>
|
||||
))}
|
||||
</SimpleGrid>
|
||||
</div>
|
||||
</Box>
|
||||
);
|
||||
};
|
||||
@@ -0,0 +1,3 @@
|
||||
export { LeaderboardTable } from "./LeaderboardTable";
|
||||
export { SideMenu } from "./SideMenu";
|
||||
export { TaskOption } from "./TaskOption";
|
||||
@@ -15,6 +15,7 @@ import {
|
||||
SliderThumb,
|
||||
SliderTrack,
|
||||
Spacer,
|
||||
Tooltip,
|
||||
useBoolean,
|
||||
useId,
|
||||
} from "@chakra-ui/react";
|
||||
@@ -69,11 +70,15 @@ export const FlaggableElement = (props) => {
|
||||
>
|
||||
<Grid templateColumns="1fr min-content" gap={2}>
|
||||
<PopoverAnchor>{props.children}</PopoverAnchor>
|
||||
<PopoverTrigger>
|
||||
<Button h="full">
|
||||
<FlagIcon className="w-4 text-gray-400 group-hover:text-gray-500" aria-hidden="true" />
|
||||
</Button>
|
||||
</PopoverTrigger>
|
||||
<Tooltip hasArrow label="Report" bg="red.600">
|
||||
<div>
|
||||
<PopoverTrigger>
|
||||
<Button h="full">
|
||||
<FlagIcon className="w-4 text-gray-400 group-hover:text-gray-500" aria-hidden="true" />
|
||||
</Button>
|
||||
</PopoverTrigger>
|
||||
</div>
|
||||
</Tooltip>
|
||||
</Grid>
|
||||
|
||||
<PopoverContent width="fit-content">
|
||||
|
||||
@@ -1,43 +1,11 @@
|
||||
import { Box, Button, useColorMode } from "@chakra-ui/react";
|
||||
import { Popover } from "@headlessui/react";
|
||||
import { AnimatePresence, motion } from "framer-motion";
|
||||
import { Box, Button, Text, useColorMode } from "@chakra-ui/react";
|
||||
import Image from "next/image";
|
||||
import Link from "next/link";
|
||||
import { useSession } from "next-auth/react";
|
||||
import { FaUser } from "react-icons/fa";
|
||||
|
||||
import { ColorModeIconToggle } from "../UI/ColorModeIconToggle";
|
||||
import { UserMenu } from "./UserMenu";
|
||||
|
||||
function MenuIcon(props) {
|
||||
return (
|
||||
<svg viewBox="0 0 24 24" fill="none" aria-hidden="true" {...props}>
|
||||
<path d="M5 6h14M5 18h14M5 12h14" strokeWidth={2} strokeLinecap="round" strokeLinejoin="round" />
|
||||
</svg>
|
||||
);
|
||||
}
|
||||
|
||||
function ChevronUpIcon(props) {
|
||||
return (
|
||||
<svg viewBox="0 0 24 24" fill="none" aria-hidden="true" {...props}>
|
||||
<path d="M17 14l-5-5-5 5" strokeWidth={2} strokeLinecap="round" strokeLinejoin="round" />
|
||||
</svg>
|
||||
);
|
||||
}
|
||||
|
||||
function MobileNavLink({ children, ...props }) {
|
||||
return (
|
||||
<Popover.Button
|
||||
as={Link}
|
||||
href={props.href}
|
||||
className="block text-base leading-7 tracking-tight text-gray-700"
|
||||
{...props}
|
||||
>
|
||||
{children}
|
||||
</Popover.Button>
|
||||
);
|
||||
}
|
||||
|
||||
function AccountButton() {
|
||||
const { data: session } = useSession();
|
||||
if (session) {
|
||||
@@ -53,70 +21,29 @@ function AccountButton() {
|
||||
}
|
||||
|
||||
export function Header(props) {
|
||||
const { data: session } = useSession();
|
||||
const homeURL = session ? "/dashboard" : "/";
|
||||
|
||||
const { colorMode } = useColorMode();
|
||||
const borderClass = props.transparent
|
||||
? ""
|
||||
: colorMode === "light"
|
||||
? "border-b border-gray-400"
|
||||
: "border-b border-zinc-800";
|
||||
|
||||
return (
|
||||
<nav className={`oa-basic-theme ${borderClass}`}>
|
||||
<Box className="flex mx-auto max-w-7xl justify-between py-8 px-10">
|
||||
<div className="relative z-10 flex items-center gap-16">
|
||||
<Link href="/" aria-label="Home" className="flex items-center">
|
||||
<Box className="relative z-10 flex justify-between px-4 py-4">
|
||||
<div className="relative z-10 flex items-center gap-10">
|
||||
<Link href={homeURL} aria-label="Home" className="flex items-center">
|
||||
<Image src="/images/logos/logo.svg" className="mx-auto object-fill" width="50" height="50" alt="logo" />
|
||||
<span className="text-2xl font-bold ml-3">Open Assistant</span>
|
||||
<Text fontFamily="inter" fontSize="2xl" fontWeight="bold" className="ml-3">
|
||||
Open Assistant
|
||||
</Text>
|
||||
</Link>
|
||||
</div>
|
||||
<div className="flex items-center gap-4">
|
||||
<Popover className="lg:hidden">
|
||||
{({ open }) => (
|
||||
<>
|
||||
<Popover.Button
|
||||
className="relative z-10 inline-flex items-center rounded-lg stroke-gray-900 p-2 hover:bg-gray-200/50 hover:stroke-gray-600 active:stroke-gray-900 [&:not(:focus-visible)]:focus:outline-none"
|
||||
aria-label="Toggle site navigation"
|
||||
>
|
||||
{({ open }) => (open ? <ChevronUpIcon className="h-6 w-6" /> : <MenuIcon className="h-6 w-6" />)}
|
||||
</Popover.Button>
|
||||
<AnimatePresence initial={false}>
|
||||
{open && (
|
||||
<>
|
||||
<Popover.Overlay
|
||||
static
|
||||
as={motion.div}
|
||||
initial={{ opacity: 0 }}
|
||||
animate={{ opacity: 1 }}
|
||||
exit={{ opacity: 0 }}
|
||||
className="fixed inset-0 z-1 bg-gray-300/60 backdrop-blur"
|
||||
/>
|
||||
<Popover.Panel
|
||||
static
|
||||
as={motion.div}
|
||||
initial={{ opacity: 0, y: -32 }}
|
||||
animate={{ opacity: 1, y: 0 }}
|
||||
exit={{
|
||||
opacity: 0,
|
||||
y: -32,
|
||||
transition: { duration: 0.2 },
|
||||
}}
|
||||
className="absolute inset-x-0 top-0 z-0 origin-top rounded-b-2xl bg-white px-6 pb-6 pt-32 shadow-2xl shadow-gray-900/20"
|
||||
>
|
||||
<div className="space-y-4">
|
||||
<MobileNavLink href="/#join-us">Join Us</MobileNavLink>
|
||||
<MobileNavLink href="/#faqs">FAQs</MobileNavLink>
|
||||
</div>
|
||||
<div className="mt-8 flex flex-col gap-4"></div>
|
||||
</Popover.Panel>
|
||||
</>
|
||||
)}
|
||||
</AnimatePresence>
|
||||
</>
|
||||
)}
|
||||
</Popover>
|
||||
<AccountButton />
|
||||
<UserMenu />
|
||||
<ColorModeIconToggle className="ml-5" />
|
||||
</div>
|
||||
</Box>
|
||||
</nav>
|
||||
|
||||
@@ -1,7 +1,8 @@
|
||||
import { useColorMode } from "@chakra-ui/react";
|
||||
import { Text, useColorMode } from "@chakra-ui/react";
|
||||
import { AnimatePresence, motion } from "framer-motion";
|
||||
import Link from "next/link";
|
||||
import { useState } from "react";
|
||||
import { colors } from "styles/Theme/colors";
|
||||
|
||||
export function NavLinks(): JSX.Element {
|
||||
const [hoveredIndex, setHoveredIndex] = useState(null);
|
||||
@@ -14,8 +15,8 @@ export function NavLinks(): JSX.Element {
|
||||
return (
|
||||
<>
|
||||
{[
|
||||
["Join Us", "/#join-us"],
|
||||
["FAQ", "/#faq"],
|
||||
["Join Us", "/#join-us"],
|
||||
].map(([label, href], index) => (
|
||||
<Link
|
||||
key={label}
|
||||
@@ -38,7 +39,9 @@ export function NavLinks(): JSX.Element {
|
||||
/>
|
||||
)}
|
||||
</AnimatePresence>
|
||||
<span className="relative z-10">{label}</span>
|
||||
<Text color={colorMode === "light" ? colors.light.text : colors.dark.text} className="relative z-10">
|
||||
{label}
|
||||
</Text>
|
||||
</Link>
|
||||
))}
|
||||
</>
|
||||
|
||||
@@ -1,25 +1,33 @@
|
||||
import { Box, useColorModeValue } from "@chakra-ui/react";
|
||||
import { Box, Link, Text, useColorModeValue } from "@chakra-ui/react";
|
||||
import { Popover } from "@headlessui/react";
|
||||
import { AnimatePresence, motion } from "framer-motion";
|
||||
import Image from "next/image";
|
||||
import { signOut, useSession } from "next-auth/react";
|
||||
import React from "react";
|
||||
import { FaCog, FaSignOutAlt } from "react-icons/fa";
|
||||
import { FiLayout, FiLogOut, FiSettings } from "react-icons/fi";
|
||||
|
||||
export function UserMenu() {
|
||||
const { data: session } = useSession();
|
||||
const backgroundColor = useColorModeValue("#FFFFFF", "#000000");
|
||||
const backgroundColor = useColorModeValue("white", "gray.700");
|
||||
const accentColor = useColorModeValue("gray.300", "gray.600");
|
||||
|
||||
if (!session) {
|
||||
return <></>;
|
||||
}
|
||||
if (session && session.user) {
|
||||
const accountOptions = [
|
||||
{
|
||||
name: "Dashboard",
|
||||
href: "/dashboard",
|
||||
desc: "Dashboard",
|
||||
icon: FiLayout,
|
||||
//For future use
|
||||
},
|
||||
{
|
||||
name: "Account Settings",
|
||||
href: "/account",
|
||||
desc: "Account Settings",
|
||||
icon: FaCog,
|
||||
icon: FiSettings,
|
||||
//For future use
|
||||
},
|
||||
];
|
||||
@@ -28,18 +36,22 @@ export function UserMenu() {
|
||||
{({ open }) => (
|
||||
<>
|
||||
<Popover.Button aria-label="Toggle Account Options" className="flex">
|
||||
<div className="flex items-center gap-4 p-1 lg:pr-6 rounded-full border border-slate-300/70 hover:bg-gray-200/50 transition-colors duration-300">
|
||||
<Box
|
||||
borderWidth="1px"
|
||||
borderColor={accentColor}
|
||||
className="flex items-center gap-4 p-1 lg:pr-6 rounded-full transition-colors duration-300"
|
||||
>
|
||||
<Image
|
||||
src="/images/temp-avatars/av1.jpg"
|
||||
src={session.user.image || "/images/temp-avatars/av1.jpg"}
|
||||
alt="Profile Picture"
|
||||
width="40"
|
||||
height="40"
|
||||
width="36"
|
||||
height="36"
|
||||
className="rounded-full"
|
||||
></Image>
|
||||
<p data-cy="username" className="hidden lg:flex">
|
||||
{session.user.name || session.user.email}
|
||||
</p>
|
||||
</div>
|
||||
</Box>
|
||||
</Popover.Button>
|
||||
<AnimatePresence initial={false}>
|
||||
{open && (
|
||||
@@ -54,35 +66,45 @@ export function UserMenu() {
|
||||
y: -10,
|
||||
transition: { duration: 0.2 },
|
||||
}}
|
||||
className="absolute right-0 mt-3 w-screen bg-inherit max-w-xs p-4 rounded-md border border-slate-300/70"
|
||||
>
|
||||
<Box className="flex flex-col gap-1">
|
||||
{accountOptions.map((item) => (
|
||||
<a
|
||||
key={item.name}
|
||||
href={item.href}
|
||||
aria-label={item.desc}
|
||||
className="flex items-center rounded-md hover:bg-gray-200/50"
|
||||
<Box
|
||||
bg={backgroundColor}
|
||||
borderWidth="1px"
|
||||
borderColor={accentColor}
|
||||
borderRadius="xl"
|
||||
className="absolute right-0 mt-3 w-screen max-w-xs p-4"
|
||||
>
|
||||
<Box className="flex flex-col gap-1">
|
||||
{accountOptions.map((item) => (
|
||||
<Link
|
||||
key={item.name}
|
||||
href={item.href}
|
||||
aria-label={item.desc}
|
||||
className="flex items-center"
|
||||
bg={backgroundColor}
|
||||
_hover={{ textDecoration: "none" }}
|
||||
>
|
||||
<div className="p-4">
|
||||
<item.icon className="text-blue-500" aria-hidden="true" />
|
||||
</div>
|
||||
<div>
|
||||
<Text fontFamily="inter">{item.name}</Text>
|
||||
</div>
|
||||
</Link>
|
||||
))}
|
||||
<Link
|
||||
className="flex items-center rounded-md cursor-pointer"
|
||||
_hover={{ textDecoration: "none" }}
|
||||
onClick={() => signOut({ callbackUrl: "/" })}
|
||||
>
|
||||
<div className="p-4">
|
||||
<item.icon aria-hidden="true" />
|
||||
<FiLogOut className="text-blue-500" />
|
||||
</div>
|
||||
<div>
|
||||
<p>{item.name}</p>
|
||||
<Text fontFamily="inter">Sign Out</Text>
|
||||
</div>
|
||||
</a>
|
||||
))}
|
||||
<a
|
||||
className="flex items-center rounded-md hover:bg-gray-100 cursor-pointer"
|
||||
onClick={() => signOut({ callbackUrl: "/" })}
|
||||
>
|
||||
<div className="p-4">
|
||||
<FaSignOutAlt />
|
||||
</div>
|
||||
<div>
|
||||
<p>Sign Out</p>
|
||||
</div>
|
||||
</a>
|
||||
</Link>
|
||||
</Box>
|
||||
</Box>
|
||||
</Popover.Panel>
|
||||
</Box>
|
||||
|
||||
@@ -25,4 +25,11 @@ export const getTransparentHeaderLayout = (page: React.ReactElement) => (
|
||||
</div>
|
||||
);
|
||||
|
||||
export const getDashboardLayout = (page: React.ReactElement) => (
|
||||
<div className="grid grid-rows-[min-content_1fr_min-content] h-full justify-items-stretch">
|
||||
<Header transparent={true} />
|
||||
{page}
|
||||
</div>
|
||||
);
|
||||
|
||||
export const noLayout = (page: React.ReactElement) => page;
|
||||
|
||||
@@ -0,0 +1,12 @@
|
||||
import { Box, CircularProgress, Stack, StackDivider, useColorModeValue } from "@chakra-ui/react";
|
||||
import { MessageTableEntry } from "./MessageTableEntry";
|
||||
|
||||
export function MessageTable({ messages }) {
|
||||
return (
|
||||
<Stack divider={<StackDivider />} spacing="4">
|
||||
{messages.map((item, idx) => (
|
||||
<MessageTableEntry item={item} idx={idx} key={item.id} />
|
||||
))}
|
||||
</Stack>
|
||||
);
|
||||
}
|
||||
@@ -0,0 +1,24 @@
|
||||
import { Avatar, Box, HStack, LinkBox, useColorModeValue } from "@chakra-ui/react";
|
||||
import { boolean } from "boolean";
|
||||
import NextLink from "next/link";
|
||||
import { FlaggableElement } from "../FlaggableElement";
|
||||
|
||||
export function MessageTableEntry({ item, idx }) {
|
||||
const bgColor = useColorModeValue(idx % 2 === 0 ? "bg-slate-800" : "bg-black", "bg-sky-900");
|
||||
|
||||
return (
|
||||
<FlaggableElement text={item.text} post_id={item.id} key={`flag_${item.id}`}>
|
||||
<HStack>
|
||||
<Avatar
|
||||
name={`${boolean(item.is_assistant) ? "Assitant" : "User"}`}
|
||||
src={`${boolean(item.is_assistant) ? "/images/logos/logo.png" : "/images/temp-avatars/av1.jpg"}`}
|
||||
/>
|
||||
<LinkBox className={`p-4 rounded-md text-white whitespace-pre-wrap ${bgColor} text-white w-full`}>
|
||||
<NextLink href={`/messages/${item.id}`} passHref>
|
||||
{item.text}
|
||||
</NextLink>
|
||||
</LinkBox>
|
||||
</HStack>
|
||||
</FlaggableElement>
|
||||
);
|
||||
}
|
||||
@@ -0,0 +1,78 @@
|
||||
import { Container } from "./Container";
|
||||
|
||||
const Roadmap = () => {
|
||||
return (
|
||||
<Container className="">
|
||||
<div className="py-32">
|
||||
<h2 className="text-4xl mb-16">Our Roadmap</h2>
|
||||
<div className="flex flex-col items-center space-y-8 md:space-y-0 md:items-start md:flex-row md:justify-between">
|
||||
<div className="flex flex-col items-center space-y-4">
|
||||
<div className="h-[5rem] w-[5rem] border-4 border-[#a72a1e] rounded-full flex items-center justify-center">
|
||||
<p className="font-bold text-[#a72a1e] text-center">ASAP</p>
|
||||
</div>
|
||||
<h4 className="font-bold text-xl text-[#a72a1e] text-center max-w-[10rem]">Minimum Viable Prototype</h4>
|
||||
<ul className="ml-6 md:ml-8 lg:ml-6 space-y-4 text-[#a72a1e] list-disc">
|
||||
<li>Data Collection Pipeline</li>
|
||||
<li>RL on Human Feedback</li>
|
||||
<li>Assistant v1 usable</li>
|
||||
<li>Out January 2023!</li>
|
||||
</ul>
|
||||
</div>
|
||||
<div>
|
||||
<span className="w-[4vw] h-[4px] mt-8 bg-[#a72a1e] rounded-full hidden md:block" />
|
||||
</div>
|
||||
<span className="w-[4px] h-16 bg-[#a72a1e] rounded-full block md:hidden" />
|
||||
<div className="flex flex-col items-center space-y-4">
|
||||
<div className="h-[5rem] w-[5rem] border-4 border-[#858585] rounded-full flex items-center justify-center">
|
||||
<p className="font-bold text-[#858585] text-center">
|
||||
Q1
|
||||
<br />
|
||||
2023
|
||||
</p>
|
||||
</div>
|
||||
<h4 className="font-bold text-xl text-[#858585] text-center max-w-[10rem]">Growing Up</h4>
|
||||
<ul className="ml-6 md:ml-8 lg:ml-6 space-y-4 text-[#858585] list-disc">
|
||||
<li>Retrieval Augmentation</li>
|
||||
<li>Rapid Personalization</li>
|
||||
<li>Using External Tools</li>
|
||||
</ul>
|
||||
</div>
|
||||
<div>
|
||||
<span className="w-[4vw] h-[4px] mt-8 bg-[#858585] rounded-full hidden md:block" />
|
||||
</div>
|
||||
<span className="w-[4px] h-16 bg-[#858585] rounded-full block md:hidden" />
|
||||
<div className="flex flex-col items-center space-y-4">
|
||||
<div className="h-[5rem] w-[5rem] border-4 border-[#858585] rounded-full flex items-center justify-center">
|
||||
<p className="font-bold text-[#858585] text-center">
|
||||
Q2
|
||||
<br />
|
||||
2023
|
||||
</p>
|
||||
</div>
|
||||
<h4 className="font-bold text-xl text-[#858585] text-center max-w-[10rem]">Growing Up</h4>
|
||||
<ul className="ml-6 md:ml-8 lg:ml-6 space-y-4 text-[#858585] list-disc">
|
||||
<li>Third-Party Extentions</li>
|
||||
<li>Device Control</li>
|
||||
<li>Multi-Modality</li>
|
||||
</ul>
|
||||
</div>
|
||||
<div>
|
||||
<span className="w-[4vw] h-[4px] mt-8 bg-[#858585] rounded-full hidden md:block" />
|
||||
</div>
|
||||
<span className="w-[4px] h-16 bg-[#858585] rounded-full block md:hidden" />
|
||||
<div className="flex flex-col items-center space-y-4">
|
||||
<div className="h-[5rem] w-[5rem] border-4 border-[#858585] rounded-full flex items-center justify-center">
|
||||
<p className="font-bold text-[#858585] text-center">...</p>
|
||||
</div>
|
||||
<h4 className="font-bold text-xl text-[#858585] text-center max-w-[10rem]">Growing Up</h4>
|
||||
<ul className="ml-6 md:ml-8 lg:ml-6 space-y-4 text-[#858585] list-disc">
|
||||
<li>What do you need?</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</Container>
|
||||
);
|
||||
};
|
||||
|
||||
export default Roadmap;
|
||||
@@ -0,0 +1,50 @@
|
||||
import { Container } from "./Container";
|
||||
|
||||
const Services = () => {
|
||||
return (
|
||||
<div className="bg-white py-32 border-t-[1px] border-gray-150">
|
||||
<Container className="">
|
||||
<div className="grid grid-cols-1 lg:grid-cols-10 lg:grid-rows-2">
|
||||
<div className="grid col-span-3 row-span-2">
|
||||
<div className="min-h-[17.5rem] px-12 sm:px-16 row-span-1 flex flex-col justify-center bg-[#307bf3] rounded-tl-[45px] lg:rounded-tl-none lg:rounded-bl-[45px] rounded-br-[45px] lg:rounded-br-none lg:rounded-tr-[45px]">
|
||||
<h4 className="font-bold text-white text-xl mb-4">Your Conversational Assistant</h4>
|
||||
<span className="w-8 h-[2px] bg-white mb-4 block lg:hidden" />
|
||||
<p className="text-white">State-of-the-Art chat assistant that can be personalized to your needs</p>
|
||||
</div>
|
||||
<div className="min-h-[17.5rem] px-12 sm:px-16 row-span-1 flex flex-col justify-center bg-[#275ddf] rounded-tl-[45px] rounded-br-[45px]">
|
||||
<h4 className="font-bold text-white text-xl mb-4">Interface w/ external systems</h4>
|
||||
<span className="w-8 h-[2px] bg-white mb-4 block lg:hidden" />
|
||||
<p className="text-white">
|
||||
Usage of APIs and third-party applications, described via language & demonstrations.
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
<div className="grid grid-rows-2 col-span-3 row-span-2">
|
||||
<div className="min-h-[17.5rem] px-12 sm:px-16 row-span-1 flex flex-col justify-center bg-[#307bf3] lg:bg-[#275ddf] rounded-tl-[45px] rounded-br-[45px]">
|
||||
<h4 className="font-bold text-white text-xl mb-4">Retrieval via Search Engines</h4>
|
||||
<span className="w-8 h-[2px] bg-white mb-4 block lg:hidden" />
|
||||
<p className="text-white">External, upgradeable knowledge: No need for billions of parameters.</p>
|
||||
</div>
|
||||
<div className="min-h-[17.5rem] px-12 sm:px-16 row-span-1 flex flex-col justify-center bg-[#275ddf] lg:bg-[#307bf3] rounded-tl-[45px] lg:rounded-tl-none lg:rounded-bl-[45px] rounded-br-[45px] lg:rounded-br-none lg:rounded-tr-[45px]">
|
||||
<h4 className="font-bold text-white text-xl mb-4">A building block for developers</h4>
|
||||
<span className="w-8 h-[2px] bg-white mb-4 block lg:hidden" />
|
||||
<p className="text-white">Integrate OpenAssistant into your application.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div className="px-12 sm:px-16 py-20 lg:p-20 col-span-4 row-span-2 bg-[#1a44a1] lg:flex lg:flex-col lg:justify-center rounded-tl-[45px] rounded-br-[45px] lg:rounded-tr-[80px] lg:rounded-tl-none lg:rounded-br-none">
|
||||
<h4 className="font-bold text-white text-xl mb-4">OpenAssistant unifies all knowledge work in one place</h4>
|
||||
<span className="w-8 h-[2px] bg-white mb-4 block lg:hidden" />
|
||||
<ul className="ml-4 sm:ml-12 mt-8 space-y-4 list-disc text-white">
|
||||
<li>Uses modern deep learning</li>
|
||||
<li>Runs on consumer hardware</li>
|
||||
<li>Trains on human feedback</li>
|
||||
<li>Free and open</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</Container>
|
||||
</div>
|
||||
);
|
||||
};
|
||||
|
||||
export default Services;
|
||||
@@ -18,6 +18,7 @@ import {
|
||||
} from "@dnd-kit/sortable";
|
||||
import { ReactNode, useEffect, useState } from "react";
|
||||
|
||||
import { CollapsableText } from "../CollapsableText";
|
||||
import { SortableItem } from "./SortableItem";
|
||||
|
||||
export interface SortableProps {
|
||||
@@ -64,7 +65,7 @@ export const Sortable = (props: SortableProps) => {
|
||||
<Flex direction="column" gap={2} className={extraClasses}>
|
||||
{itemsWithIds.map(({ id, item }) => (
|
||||
<SortableItem key={id} id={id}>
|
||||
{item}
|
||||
<CollapsableText text={item} />
|
||||
</SortableItem>
|
||||
))}
|
||||
</Flex>
|
||||
|
||||
@@ -4,7 +4,7 @@ import { SkipButton } from "src/components/Buttons/Skip";
|
||||
import { SubmitButton } from "src/components/Buttons/Submit";
|
||||
import { TaskInfo } from "src/components/TaskInfo/TaskInfo";
|
||||
|
||||
interface TaskControlsProps {
|
||||
export interface TaskControlsProps {
|
||||
// we need a task type
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
tasks: any[];
|
||||
@@ -30,11 +30,11 @@ export const TaskControls = (props: TaskControlsProps) => {
|
||||
<Flex justify="center" ml="auto" gap={2}>
|
||||
<SkipButton>Skip</SkipButton>
|
||||
{endTask.task.type !== "task_done" ? (
|
||||
<SubmitButton data-cy="submit" onClick={() => props.onSubmitResponse(props.tasks[0])}>
|
||||
<SubmitButton colorScheme="blue" data-cy="submit" onClick={() => props.onSubmitResponse(props.tasks[0])}>
|
||||
Submit
|
||||
</SubmitButton>
|
||||
) : (
|
||||
<SubmitButton data-cy="next-task" onClick={props.onSkip}>
|
||||
<SubmitButton colorScheme="green" data-cy="next-task" onClick={props.onSkip}>
|
||||
Next Task
|
||||
</SubmitButton>
|
||||
)}
|
||||
|
||||
@@ -0,0 +1,60 @@
|
||||
import {
|
||||
Button,
|
||||
Flex,
|
||||
Modal,
|
||||
ModalBody,
|
||||
ModalCloseButton,
|
||||
ModalContent,
|
||||
ModalFooter,
|
||||
ModalHeader,
|
||||
ModalOverlay,
|
||||
useDisclosure,
|
||||
} from "@chakra-ui/react";
|
||||
import { TaskControls, TaskControlsProps } from "./TaskControls";
|
||||
|
||||
interface TaskControlsOverridableProps extends TaskControlsProps {
|
||||
isValid: boolean;
|
||||
prepareForSubmit: () => void;
|
||||
}
|
||||
|
||||
export const TaskControlsOverridable = (props: TaskControlsOverridableProps) => {
|
||||
const { isValid, onSubmitResponse, ...rest } = props;
|
||||
const { isOpen: isModalOpen, onOpen: onOpenModal, onClose: onModalClose } = useDisclosure();
|
||||
|
||||
const unchangedResponsePrompt = () => {
|
||||
onOpenModal();
|
||||
|
||||
// Ideally this happens when the user clicks submit, but we can't
|
||||
// reliably wait for it to be executed before submitting the response
|
||||
// without significant refactoring.
|
||||
// As a result, modal will only display once even if the user doesn't proceed
|
||||
props.prepareForSubmit();
|
||||
};
|
||||
|
||||
const onSubmitResponseOverride = () => {
|
||||
onSubmitResponse(props.tasks[0]);
|
||||
onModalClose();
|
||||
};
|
||||
|
||||
return (
|
||||
<>
|
||||
<Modal isOpen={isModalOpen} onClose={onModalClose} isCentered>
|
||||
<ModalOverlay />
|
||||
<ModalContent>
|
||||
<ModalCloseButton />
|
||||
<ModalHeader>Order Unchanged</ModalHeader>
|
||||
<ModalBody>You have not changed the order of the prompts. Are you sure you would like to submit?</ModalBody>
|
||||
<ModalFooter>
|
||||
<Flex justify="center" ml="auto" gap={2}>
|
||||
<Button variant={"ghost"} onClick={onModalClose}>
|
||||
Cancel
|
||||
</Button>
|
||||
<Button onClick={onSubmitResponseOverride}>Submit anyway</Button>
|
||||
</Flex>
|
||||
</ModalFooter>
|
||||
</ModalContent>
|
||||
</Modal>
|
||||
<TaskControls onSubmitResponse={isValid ? props.onSubmitResponse : unchangedResponsePrompt} {...rest} />
|
||||
</>
|
||||
);
|
||||
};
|
||||
@@ -0,0 +1,25 @@
|
||||
import { Container } from "./Container";
|
||||
import Image from "next/image";
|
||||
|
||||
const Vision = () => {
|
||||
return (
|
||||
<div className="bg-gray-900 py-20">
|
||||
<Container className="">
|
||||
<div className="grid gap-16 items-center py-20 md:py-32 lg:grid-cols-2">
|
||||
<div>
|
||||
<h2 className="text-4xl text-white mb-6">Our Vision</h2>
|
||||
<p className="text-2xl text-gray-400">
|
||||
We want OpenAssistant to be the single, unifying platform that all other systems use to interface with
|
||||
humans.
|
||||
</p>
|
||||
</div>
|
||||
<div className="m-auto rounded-tl-[45px] rounded-br-[45px] overflow-hidden">
|
||||
<Image src="/images/temp-avatars/av2.jpg" width={450} height={450} alt="temp-image" />
|
||||
</div>
|
||||
</div>
|
||||
</Container>
|
||||
</div>
|
||||
);
|
||||
};
|
||||
|
||||
export default Vision;
|
||||
@@ -0,0 +1,98 @@
|
||||
import { JWT } from "next-auth/jwt";
|
||||
|
||||
declare global {
|
||||
// eslint-disable-next-line no-var
|
||||
var oasstApiClient: OasstApiClient | undefined;
|
||||
}
|
||||
|
||||
class OasstError {
|
||||
message: string;
|
||||
errorCode: number;
|
||||
httpStatusCode: number;
|
||||
|
||||
constructor(message: string, errorCode: number, httpStatusCode: number) {
|
||||
this.message = message;
|
||||
this.errorCode = errorCode;
|
||||
this.httpStatusCode = httpStatusCode;
|
||||
}
|
||||
}
|
||||
|
||||
export class OasstApiClient {
|
||||
constructor(private readonly oasstApiUrl: string, private readonly oasstApiKey: string) {}
|
||||
|
||||
private async post(path: string, body: any): Promise<any> {
|
||||
const resp = await fetch(`${this.oasstApiUrl}${path}`, {
|
||||
method: "POST",
|
||||
headers: {
|
||||
"X-API-Key": this.oasstApiKey,
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
body: JSON.stringify(body),
|
||||
});
|
||||
|
||||
if (resp.status == 204) {
|
||||
return null;
|
||||
}
|
||||
|
||||
if (resp.status >= 300) {
|
||||
const errorText = await resp.text();
|
||||
try {
|
||||
const error = JSON.parse(errorText);
|
||||
throw new OasstError(error.message, error.error_code, resp.status);
|
||||
} catch (e) {
|
||||
throw new OasstError(errorText, 0, resp.status);
|
||||
}
|
||||
}
|
||||
|
||||
return await resp.json();
|
||||
}
|
||||
|
||||
// TODO return a strongly typed Task?
|
||||
// This method is used to store a task in RegisteredTask.task.
|
||||
// This is a raw Json type, so we can't use it to strongly type the task.
|
||||
async fetchTask(taskType: string, userToken: JWT): Promise<any> {
|
||||
return this.post("/api/v1/tasks/", {
|
||||
type: taskType,
|
||||
user: {
|
||||
id: userToken.sub,
|
||||
display_name: userToken.name || userToken.email,
|
||||
auth_method: "local",
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
async ackTask(taskId: string, messageId: string): Promise<void> {
|
||||
return this.post(`/api/v1/tasks/${taskId}/ack`, {
|
||||
message_id: messageId,
|
||||
});
|
||||
}
|
||||
|
||||
// TODO return a strongly typed Task?
|
||||
// This method is used to record interaction with task while fetching next task.
|
||||
// This is a raw Json type, so we can't use it to strongly type the task.
|
||||
async interactTask(
|
||||
updateType: string,
|
||||
messageId: string,
|
||||
userMessageId: string,
|
||||
content: object,
|
||||
userToken: JWT
|
||||
): Promise<any> {
|
||||
return this.post("/api/v1/tasks/interaction", {
|
||||
type: updateType,
|
||||
user: {
|
||||
id: userToken.sub,
|
||||
display_name: userToken.name || userToken.email,
|
||||
auth_method: "local",
|
||||
},
|
||||
message_id: messageId,
|
||||
user_message_id: userMessageId,
|
||||
...content,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
export const oasstApiClient =
|
||||
globalThis.oasstApiClient || new OasstApiClient(process.env.FASTAPI_URL, process.env.FASTAPI_KEY);
|
||||
if (process.env.NODE_ENV !== "production") {
|
||||
globalThis.oasstApiClient = oasstApiClient;
|
||||
}
|
||||
@@ -4,5 +4,5 @@ export { default } from "next-auth/middleware";
|
||||
* Guards all pages under `/grading` and redirects them to the sign in page.
|
||||
*/
|
||||
export const config = {
|
||||
matcher: ["/create/:path*", "/evaluate/:path*", "/account/:path*"],
|
||||
matcher: ["/create/:path*", "/evaluate/:path*", "/account/:path*", "/dashboard"],
|
||||
};
|
||||
|
||||
@@ -0,0 +1,39 @@
|
||||
import { Container } from "src/components/Container";
|
||||
import Services from "src/components/Services";
|
||||
import Vision from "src/components/Vision";
|
||||
import Roadmap from "src/components/Roadmap";
|
||||
import { CallToAction } from "src/components/CallToAction";
|
||||
import Image from "next/image";
|
||||
|
||||
const AboutPage = () => {
|
||||
return (
|
||||
<div>
|
||||
<Container className="">
|
||||
<div className="grid gap-16 items-center py-20 md:py-40 lg:grid-cols-2">
|
||||
<div className="m-auto order-2 lg:order-1">
|
||||
<Image src="/images/logos/logo.png" width={450} height={450} alt="temp-image" />
|
||||
</div>
|
||||
<div className="space-y-8 order-1 lg:order-2">
|
||||
<div>
|
||||
<h1 className="text-4xl mb-6">What is OpenAssistant?</h1>
|
||||
<p className="text-2xl">
|
||||
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems,
|
||||
and retrieve information dynamically to do so.
|
||||
</p>
|
||||
</div>
|
||||
<p className="text-2xl">
|
||||
It can be extended and personalized easily and is developed as free, open-source software.
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
</Container>
|
||||
|
||||
<Services />
|
||||
<Vision />
|
||||
<Roadmap />
|
||||
<CallToAction />
|
||||
</div>
|
||||
);
|
||||
};
|
||||
|
||||
export default AboutPage;
|
||||
@@ -7,6 +7,7 @@ import React, { useState } from "react";
|
||||
export default function Account() {
|
||||
const { data: session } = useSession();
|
||||
const [username, setUsername] = useState("");
|
||||
|
||||
const updateUser = async (e: React.SyntheticEvent) => {
|
||||
e.preventDefault();
|
||||
try {
|
||||
@@ -16,6 +17,7 @@ export default function Account() {
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify(body),
|
||||
});
|
||||
session.user.name = username;
|
||||
await Router.push("/account");
|
||||
} catch (error) {
|
||||
console.error(error);
|
||||
@@ -34,23 +36,24 @@ export default function Account() {
|
||||
content="Conversational AI for everyone. An open source project to create a chat enabled GPT LLM run by LAION and contributors around the world."
|
||||
/>
|
||||
</Head>
|
||||
<main className="h-3/4 z-0 bg-white flex flex-col items-center justify-center">
|
||||
<p>{session.user.name || "No username"}</p>
|
||||
<form onSubmit={updateUser}>
|
||||
<InputGroup>
|
||||
<Input
|
||||
onChange={(e) => setUsername(e.target.value)}
|
||||
placeholder="Edit Username"
|
||||
type="text"
|
||||
value={username}
|
||||
></Input>
|
||||
<Button disabled={!username} type="submit" value="Change">
|
||||
Submit
|
||||
</Button>
|
||||
</InputGroup>
|
||||
</form>
|
||||
<p>{session.user.email}</p>
|
||||
</main>
|
||||
<div className="oa-basic-theme">
|
||||
<main className="h-3/4 z-0 flex flex-col items-center justify-center">
|
||||
<p>{session.user.name || "No username"}</p>
|
||||
<form onSubmit={updateUser}>
|
||||
<InputGroup>
|
||||
<Input
|
||||
onChange={(e) => setUsername(e.target.value)}
|
||||
placeholder="Edit Username"
|
||||
type="text"
|
||||
value={username}
|
||||
></Input>
|
||||
<Button disabled={!username} type="submit" value="Change">
|
||||
Submit
|
||||
</Button>
|
||||
</InputGroup>
|
||||
</form>
|
||||
</main>
|
||||
</div>
|
||||
</>
|
||||
);
|
||||
}
|
||||
|
||||
@@ -19,13 +19,15 @@ export default function Account() {
|
||||
content="Conversational AI for everyone. An open source project to create a chat enabled GPT LLM run by LAION and contributors around the world."
|
||||
/>
|
||||
</Head>
|
||||
<main className="h-3/4 z-0 bg-white flex flex-col items-center justify-center">
|
||||
<p>{session.user.name || "No username"}</p>
|
||||
<Button>
|
||||
<Link href="/account/edit">Edit Username</Link>
|
||||
</Button>
|
||||
<p>{session.user.email}</p>
|
||||
</main>
|
||||
<div className="oa-basic-theme">
|
||||
<main className="h-3/4 z-0 flex flex-col items-center justify-center">
|
||||
<p>{session.user.name || "No username"}</p>
|
||||
<Button>
|
||||
<Link href="/account/edit">Edit Username</Link>
|
||||
</Button>
|
||||
<p>{session.user.email}</p>
|
||||
</main>
|
||||
</div>
|
||||
</>
|
||||
);
|
||||
}
|
||||
|
||||
@@ -59,6 +59,17 @@ if (boolean(process.env.DEBUG_LOGIN) || process.env.NODE_ENV === "development")
|
||||
);
|
||||
}
|
||||
|
||||
// Create a map of provider types to a set of admin user identifiers based on
|
||||
// the environment variables. We assume the list is separated by ',' and each
|
||||
// entry is separated by ':'.
|
||||
const adminUserMap = process.env.ADMIN_USERS.split(",").reduce((result, entry) => {
|
||||
const [authType, id] = entry.split(":");
|
||||
const s = result.get(authType) || new Set();
|
||||
s.add(id);
|
||||
result.set(authType, s);
|
||||
return result;
|
||||
}, new Map());
|
||||
|
||||
export const authOptions: AuthOptions = {
|
||||
// Ensure we can store user data in a database.
|
||||
adapter: PrismaAdapter(prisma),
|
||||
@@ -68,6 +79,56 @@ export const authOptions: AuthOptions = {
|
||||
verifyRequest: "/auth/verify",
|
||||
// error: "/auth/error", -Will be used later
|
||||
},
|
||||
callbacks: {
|
||||
/**
|
||||
* Ensure we propagate the user's role when creating the session from the
|
||||
* token.
|
||||
*/
|
||||
async session({ session, token }) {
|
||||
session.user.role = token.role;
|
||||
return session;
|
||||
},
|
||||
/**
|
||||
* When creating a token, fetch the user's role and inject it in the token.
|
||||
* This let's use forward the role to the session object.
|
||||
*/
|
||||
async jwt({ token }) {
|
||||
const { role } = await prisma.user.findUnique({
|
||||
where: { id: token.sub },
|
||||
select: { role: true },
|
||||
});
|
||||
token.role = role;
|
||||
return token;
|
||||
},
|
||||
},
|
||||
events: {
|
||||
/**
|
||||
* Update the user's role after they have successfully signed in
|
||||
*/
|
||||
async signIn({ user, account }) {
|
||||
// Get the admin list for the user's auth type.
|
||||
const adminForAccountType = adminUserMap.get(account.provider);
|
||||
|
||||
// Return early if there's no admin list.
|
||||
if (!adminForAccountType) {
|
||||
return;
|
||||
}
|
||||
|
||||
// TODO(#236): Reduce the number of times we update the role field.
|
||||
|
||||
// Update the database if the user is an admin.
|
||||
if (adminForAccountType.has(account.providerAccountId)) {
|
||||
await prisma.user.update({
|
||||
data: {
|
||||
role: "admin",
|
||||
},
|
||||
where: {
|
||||
id: user.id,
|
||||
},
|
||||
});
|
||||
}
|
||||
},
|
||||
},
|
||||
session: {
|
||||
strategy: "jwt",
|
||||
},
|
||||
|
||||
@@ -0,0 +1,24 @@
|
||||
import { getToken } from "next-auth/jwt";
|
||||
|
||||
const handler = async (req, res) => {
|
||||
const token = await getToken({ req });
|
||||
|
||||
// Return nothing if the user isn't registered.
|
||||
if (!token) {
|
||||
res.status(401).end();
|
||||
return;
|
||||
}
|
||||
|
||||
const messagesRes = await fetch(`${process.env.FASTAPI_URL}/api/v1/messages`, {
|
||||
method: "GET",
|
||||
headers: {
|
||||
"X-API-Key": process.env.FASTAPI_KEY,
|
||||
},
|
||||
});
|
||||
const messages = await messagesRes.json();
|
||||
|
||||
// Send recieved messages to the client.
|
||||
res.status(200).json(messages);
|
||||
};
|
||||
|
||||
export default handler;
|
||||
@@ -0,0 +1,29 @@
|
||||
import { getToken } from "next-auth/jwt";
|
||||
|
||||
const handler = async (req, res) => {
|
||||
const token = await getToken({ req });
|
||||
|
||||
// Return nothing if the user isn't registered.
|
||||
if (!token) {
|
||||
res.status(401).end();
|
||||
return;
|
||||
}
|
||||
|
||||
//TODO: add params if needed
|
||||
const params = new URLSearchParams({
|
||||
username: token.sub,
|
||||
});
|
||||
|
||||
const messagesRes = await fetch(`${process.env.FASTAPI_URL}/api/v1/messages?${params}`, {
|
||||
method: "GET",
|
||||
headers: {
|
||||
"X-API-Key": process.env.FASTAPI_KEY,
|
||||
},
|
||||
});
|
||||
const messages = await messagesRes.json();
|
||||
|
||||
// Send recieved messages to the client.
|
||||
res.status(200).json(messages);
|
||||
};
|
||||
|
||||
export default handler;
|
||||
@@ -1,4 +1,5 @@
|
||||
import { getToken } from "next-auth/jwt";
|
||||
import { oasstApiClient } from "src/lib/oasst_api_client";
|
||||
import prisma from "src/lib/prismadb";
|
||||
|
||||
/**
|
||||
@@ -21,24 +22,7 @@ const handler = async (req, res) => {
|
||||
}
|
||||
|
||||
// Fetch the new task.
|
||||
//
|
||||
// This needs to be refactored into an easier to use library.
|
||||
const taskRes = await fetch(`${process.env.FASTAPI_URL}/api/v1/tasks/`, {
|
||||
method: "POST",
|
||||
headers: {
|
||||
"X-API-Key": process.env.FASTAPI_KEY,
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
body: JSON.stringify({
|
||||
type: task_type,
|
||||
user: {
|
||||
id: token.sub,
|
||||
display_name: token.name || token.email,
|
||||
auth_method: "local",
|
||||
},
|
||||
}),
|
||||
});
|
||||
const task = await taskRes.json();
|
||||
const task = await oasstApiClient.fetchTask(task_type, token);
|
||||
|
||||
// Store the task and link it to the user..
|
||||
const registeredTask = await prisma.registeredTask.create({
|
||||
@@ -53,16 +37,7 @@ const handler = async (req, res) => {
|
||||
});
|
||||
|
||||
// Update the backend with our Task ID
|
||||
await fetch(`${process.env.FASTAPI_URL}/api/v1/tasks/${task.id}/ack`, {
|
||||
method: "POST",
|
||||
headers: {
|
||||
"X-API-Key": process.env.FASTAPI_KEY,
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
body: JSON.stringify({
|
||||
message_id: registeredTask.id,
|
||||
}),
|
||||
});
|
||||
await oasstApiClient.ackTask(task.id, registeredTask.id);
|
||||
|
||||
// Send the results to the client.
|
||||
res.status(200).json(registeredTask);
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
import { getToken } from "next-auth/jwt";
|
||||
import { oasstApiClient } from "src/lib/oasst_api_client";
|
||||
import prisma from "src/lib/prismadb";
|
||||
|
||||
/**
|
||||
@@ -34,27 +35,7 @@ const handler = async (req, res) => {
|
||||
},
|
||||
});
|
||||
|
||||
// Send the interaction to the Task Backend. This automatically fetches the
|
||||
// next task in the sequence (or the done task).
|
||||
const interactionRes = await fetch(`${process.env.FASTAPI_URL}/api/v1/tasks/interaction`, {
|
||||
method: "POST",
|
||||
headers: {
|
||||
"X-API-Key": process.env.FASTAPI_KEY,
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
body: JSON.stringify({
|
||||
type: update_type,
|
||||
user: {
|
||||
id: token.sub,
|
||||
display_name: token.name || token.email,
|
||||
auth_method: "local",
|
||||
},
|
||||
message_id: id,
|
||||
user_message_id: interaction.id,
|
||||
...content,
|
||||
}),
|
||||
});
|
||||
const newTask = await interactionRes.json();
|
||||
const newTask = await oasstApiClient.interactTask(update_type, id, interaction.id, content, token);
|
||||
|
||||
// Stores the new task with our database.
|
||||
const newRegisteredTask = await prisma.registeredTask.create({
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
import { getSession } from "next-auth/react";
|
||||
import prisma from "../../lib/prismadb";
|
||||
|
||||
// POST /api/post
|
||||
// Required fields in body: title
|
||||
|
||||
@@ -15,13 +15,13 @@ function Signin({ csrfToken, providers }) {
|
||||
const emailEl = useRef(null);
|
||||
const signinWithEmail = (ev: React.FormEvent) => {
|
||||
ev.preventDefault();
|
||||
signIn(email.id, { callbackUrl: "/", email: emailEl.current.value });
|
||||
signIn(email.id, { callbackUrl: "/dashboard", email: emailEl.current.value });
|
||||
};
|
||||
|
||||
const debugUsernameEl = useRef(null);
|
||||
function signinWithDebugCredentials(ev: React.FormEvent) {
|
||||
ev.preventDefault();
|
||||
signIn(credentials.id, { callbackUrl: "/", username: debugUsernameEl.current.value });
|
||||
signIn(credentials.id, { callbackUrl: "/dashboard", username: debugUsernameEl.current.value });
|
||||
}
|
||||
|
||||
const { colorMode } = useColorMode();
|
||||
@@ -98,7 +98,8 @@ function Signin({ csrfToken, providers }) {
|
||||
</Button>
|
||||
)}
|
||||
</Stack>
|
||||
<div className="pt-10 text-center">
|
||||
<hr className="mt-14 mb-4 h-px bg-gray-200 border-0" />
|
||||
<div className="text-center">
|
||||
By signing up you agree to our <br></br>
|
||||
<Link href="/terms-of-service" aria-label="Terms of Service" className="hover:underline underline-offset-4">
|
||||
<b>Terms of Service</b>
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { Container, Textarea } from "@chakra-ui/react";
|
||||
import { useColorMode } from "@chakra-ui/react";
|
||||
import { useRef, useState } from "react";
|
||||
import { useEffect, useRef, useState } from "react";
|
||||
import { LoadingScreen } from "src/components/Loading/LoadingScreen";
|
||||
import { Messages } from "src/components/Messages";
|
||||
import { TaskControls } from "src/components/Survey/TaskControls";
|
||||
@@ -21,6 +21,12 @@ const AssistantReply = () => {
|
||||
},
|
||||
});
|
||||
|
||||
useEffect(() => {
|
||||
if (tasks.length == 0) {
|
||||
mutate();
|
||||
}
|
||||
}, [tasks]);
|
||||
|
||||
const { trigger } = useSWRMutation("/api/update_task", poster, {
|
||||
onSuccess: async (data) => {
|
||||
const newTask = await data.json();
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { Container, Textarea } from "@chakra-ui/react";
|
||||
import { useColorMode } from "@chakra-ui/react";
|
||||
import { useRef, useState } from "react";
|
||||
import { useEffect, useRef, useState } from "react";
|
||||
import { LoadingScreen } from "src/components/Loading/LoadingScreen";
|
||||
import { TaskControls } from "src/components/Survey/TaskControls";
|
||||
import { TwoColumnsWithCards } from "src/components/Survey/TwoColumnsWithCards";
|
||||
@@ -27,6 +27,12 @@ const InitialPrompt = () => {
|
||||
},
|
||||
});
|
||||
|
||||
useEffect(() => {
|
||||
if (tasks.length == 0) {
|
||||
mutate();
|
||||
}
|
||||
}, [tasks]);
|
||||
|
||||
const submitResponse = (task: { id: string }) => {
|
||||
const text = inputRef.current.value.trim();
|
||||
trigger({
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { Textarea } from "@chakra-ui/react";
|
||||
import { useColorMode } from "@chakra-ui/react";
|
||||
import { useRef, useState } from "react";
|
||||
import { useEffect, useRef, useState } from "react";
|
||||
import { LoadingScreen } from "src/components/Loading/LoadingScreen";
|
||||
import { Messages } from "src/components/Messages";
|
||||
import { TaskControls } from "src/components/Survey/TaskControls";
|
||||
@@ -21,6 +21,12 @@ const UserReply = () => {
|
||||
},
|
||||
});
|
||||
|
||||
useEffect(() => {
|
||||
if (tasks.length == 0) {
|
||||
mutate();
|
||||
}
|
||||
}, [tasks]);
|
||||
|
||||
const { trigger } = useSWRMutation("/api/update_task", poster, {
|
||||
onSuccess: async (data) => {
|
||||
const newTask = await data.json();
|
||||
|
||||
@@ -0,0 +1,33 @@
|
||||
import { Box, useColorMode } from "@chakra-ui/react";
|
||||
import Head from "next/head";
|
||||
|
||||
import { getDashboardLayout } from "src/components/Layout";
|
||||
import { LeaderboardTable, SideMenu, TaskOption } from "src/components/Dashboard";
|
||||
import { colors } from "styles/Theme/colors";
|
||||
|
||||
const Dashboard = () => {
|
||||
const { colorMode } = useColorMode();
|
||||
return (
|
||||
<>
|
||||
<Head>
|
||||
<title>Dashboard - Open Assistant</title>
|
||||
<meta name="description" content="Chat with Open Assistant and provide feedback." />
|
||||
</Head>
|
||||
<Box backgroundColor={colorMode === "light" ? colors.light.bg : colors.dark.bg} className="sm:overflow-hidden">
|
||||
<Box className="sm:flex h-full gap-6">
|
||||
<Box className="p-6 sm:pr-0">
|
||||
<SideMenu />
|
||||
</Box>
|
||||
<Box className="flex flex-col overflow-auto p-6 sm:pl-0 gap-14">
|
||||
<TaskOption />
|
||||
<LeaderboardTable />
|
||||
</Box>
|
||||
</Box>
|
||||
</Box>
|
||||
</>
|
||||
);
|
||||
};
|
||||
|
||||
Dashboard.getLayout = (page) => getDashboardLayout(page);
|
||||
|
||||
export default Dashboard;
|
||||
@@ -1,10 +1,12 @@
|
||||
import { useColorMode } from "@chakra-ui/react";
|
||||
import Head from "next/head";
|
||||
import { useState } from "react";
|
||||
import { useEffect, useState } from "react";
|
||||
import { ContextMessages } from "src/components/ContextMessages";
|
||||
import { LoadingScreen } from "src/components/Loading/LoadingScreen";
|
||||
import { Message } from "src/components/Messages";
|
||||
import { Sortable } from "src/components/Sortable/Sortable";
|
||||
import { SurveyCard } from "src/components/Survey/SurveyCard";
|
||||
import { TaskControls } from "src/components/Survey/TaskControls";
|
||||
import { TaskControlsOverridable } from "src/components/Survey/TaskControlsOverridable";
|
||||
import fetcher from "src/lib/fetcher";
|
||||
import poster from "src/lib/poster";
|
||||
import useSWRImmutable from "swr/immutable";
|
||||
@@ -24,6 +26,12 @@ const RankAssistantReplies = () => {
|
||||
},
|
||||
});
|
||||
|
||||
useEffect(() => {
|
||||
if (tasks.length == 0) {
|
||||
mutate();
|
||||
}
|
||||
}, [tasks]);
|
||||
|
||||
const { trigger } = useSWRMutation("/api/update_task", poster, {
|
||||
onSuccess: async (data) => {
|
||||
const newTask = await data.json();
|
||||
@@ -64,6 +72,7 @@ const RankAssistantReplies = () => {
|
||||
}
|
||||
|
||||
const replies = tasks[0].task.replies as string[];
|
||||
const messages = tasks[0].task.conversation.messages as Message[];
|
||||
|
||||
return (
|
||||
<>
|
||||
@@ -77,10 +86,17 @@ const RankAssistantReplies = () => {
|
||||
<p className="text-lg py-1">
|
||||
Given the following replies, sort them from best to worst, best being first, worst being last.
|
||||
</p>
|
||||
<ContextMessages messages={messages} />
|
||||
<Sortable items={replies} onChange={setRanking} className="my-8" />
|
||||
</SurveyCard>
|
||||
|
||||
<TaskControls tasks={tasks} onSubmitResponse={submitResponse} onSkip={fetchNextTask} />
|
||||
<TaskControlsOverridable
|
||||
tasks={tasks}
|
||||
isValid={ranking.length == tasks[0].task.replies.length}
|
||||
prepareForSubmit={() => setRanking(tasks[0].task.replies.map((_, idx) => idx))}
|
||||
onSubmitResponse={submitResponse}
|
||||
onSkip={fetchNextTask}
|
||||
/>
|
||||
</div>
|
||||
</>
|
||||
);
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
import { useColorMode } from "@chakra-ui/react";
|
||||
import Head from "next/head";
|
||||
import { useState } from "react";
|
||||
import { useEffect, useState } from "react";
|
||||
import { LoadingScreen } from "src/components/Loading/LoadingScreen";
|
||||
import { Sortable } from "src/components/Sortable/Sortable";
|
||||
import { SurveyCard } from "src/components/Survey/SurveyCard";
|
||||
import { TaskControls } from "src/components/Survey/TaskControls";
|
||||
import { TaskControlsOverridable } from "src/components/Survey/TaskControlsOverridable";
|
||||
import fetcher from "src/lib/fetcher";
|
||||
import poster from "src/lib/poster";
|
||||
import useSWRImmutable from "swr/immutable";
|
||||
@@ -32,6 +32,12 @@ const RankInitialPrompts = () => {
|
||||
},
|
||||
});
|
||||
|
||||
useEffect(() => {
|
||||
if (tasks.length == 0) {
|
||||
mutate();
|
||||
}
|
||||
}, [tasks]);
|
||||
|
||||
const submitResponse = (task) => {
|
||||
trigger({
|
||||
id: task.id,
|
||||
@@ -79,7 +85,13 @@ const RankInitialPrompts = () => {
|
||||
<Sortable items={tasks[0].task.prompts} onChange={setRanking} className="my-8" />
|
||||
</SurveyCard>
|
||||
|
||||
<TaskControls tasks={tasks} onSubmitResponse={submitResponse} onSkip={fetchNextTask} />
|
||||
<TaskControlsOverridable
|
||||
tasks={tasks}
|
||||
isValid={ranking.length == tasks[0].task.prompts.length}
|
||||
prepareForSubmit={() => setRanking(tasks[0].task.prompts.map((_, idx) => idx))}
|
||||
onSubmitResponse={submitResponse}
|
||||
onSkip={fetchNextTask}
|
||||
/>
|
||||
</div>
|
||||
</>
|
||||
);
|
||||
|
||||
@@ -1,10 +1,12 @@
|
||||
import { useColorMode } from "@chakra-ui/react";
|
||||
import Head from "next/head";
|
||||
import { useState } from "react";
|
||||
import { useEffect, useState } from "react";
|
||||
import { ContextMessages } from "src/components/ContextMessages";
|
||||
import { LoadingScreen } from "src/components/Loading/LoadingScreen";
|
||||
import { Message } from "src/components/Messages";
|
||||
import { Sortable } from "src/components/Sortable/Sortable";
|
||||
import { SurveyCard } from "src/components/Survey/SurveyCard";
|
||||
import { TaskControls } from "src/components/Survey/TaskControls";
|
||||
import { TaskControlsOverridable } from "src/components/Survey/TaskControlsOverridable";
|
||||
import fetcher from "src/lib/fetcher";
|
||||
import poster from "src/lib/poster";
|
||||
import useSWRImmutable from "swr/immutable";
|
||||
@@ -24,6 +26,12 @@ const RankUserReplies = () => {
|
||||
},
|
||||
});
|
||||
|
||||
useEffect(() => {
|
||||
if (tasks.length == 0) {
|
||||
mutate();
|
||||
}
|
||||
}, [tasks]);
|
||||
|
||||
const { trigger } = useSWRMutation("/api/update_task", poster, {
|
||||
onSuccess: async (data) => {
|
||||
const newTask = await data.json();
|
||||
@@ -63,6 +71,7 @@ const RankUserReplies = () => {
|
||||
);
|
||||
}
|
||||
const replies = tasks[0].task.replies as string[];
|
||||
const messages = tasks[0].task.conversation.messages as Message[];
|
||||
|
||||
return (
|
||||
<>
|
||||
@@ -76,10 +85,17 @@ const RankUserReplies = () => {
|
||||
<p className="text-lg py-1">
|
||||
Given the following replies, sort them from best to worst, best being first, worst being last.
|
||||
</p>
|
||||
<ContextMessages messages={messages} />
|
||||
<Sortable items={replies} onChange={setRanking} className="my-8" />
|
||||
</SurveyCard>
|
||||
|
||||
<TaskControls tasks={tasks} onSubmitResponse={submitResponse} onSkip={fetchNextTask} />
|
||||
<TaskControlsOverridable
|
||||
tasks={tasks}
|
||||
isValid={ranking.length == tasks[0].task.replies.length}
|
||||
prepareForSubmit={() => setRanking(tasks[0].task.replies.map((_, idx) => idx))}
|
||||
onSubmitResponse={submitResponse}
|
||||
onSkip={fetchNextTask}
|
||||
/>
|
||||
</div>
|
||||
</>
|
||||
);
|
||||
|
||||
@@ -1,16 +1,10 @@
|
||||
import Head from "next/head";
|
||||
import { useSession } from "next-auth/react";
|
||||
import { CallToAction } from "src/components/CallToAction";
|
||||
import { Faq } from "src/components/Faq";
|
||||
import { Footer } from "src/components/Footer";
|
||||
import { Header } from "src/components/Header";
|
||||
import { Hero } from "src/components/Hero";
|
||||
import { getTransparentHeaderLayout } from "src/components/Layout";
|
||||
import { TaskSelection } from "src/components/TaskSelection";
|
||||
|
||||
const Home = () => {
|
||||
const { data: session } = useSession();
|
||||
|
||||
return (
|
||||
<>
|
||||
<Head>
|
||||
@@ -20,15 +14,11 @@ const Home = () => {
|
||||
content="Conversational AI for everyone. An open source project to create a chat enabled GPT LLM run by LAION and contributors around the world."
|
||||
/>
|
||||
</Head>
|
||||
{session ? (
|
||||
<TaskSelection />
|
||||
) : (
|
||||
<main className="oa-basic-theme">
|
||||
<Hero />
|
||||
<CallToAction />
|
||||
<Faq />
|
||||
</main>
|
||||
)}
|
||||
<main className="oa-basic-theme">
|
||||
<Hero />
|
||||
<CallToAction />
|
||||
<Faq />
|
||||
</main>
|
||||
</>
|
||||
);
|
||||
};
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user