mirror of
https://github.com/wassname/Open-Assistant.git
synced 2026-07-20 12:10:50 +08:00
Merge branch 'LAION-AI:main' into messageNavigation
This commit is contained in:
jojopirker
@@ -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
|
||||
|
||||
+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.
|
||||
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 24 KiB |
@@ -1,3 +1,4 @@
|
||||
__pycache__
|
||||
.env
|
||||
notes.txt
|
||||
venv
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -206,3 +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
|
||||
|
||||
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 |
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."""
|
||||
|
||||
+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
|
||||
});
|
||||
@@ -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",
|
||||
|
||||
@@ -41,6 +41,7 @@ model User {
|
||||
email String? @unique
|
||||
emailVerified DateTime?
|
||||
image String?
|
||||
role String @default("general")
|
||||
|
||||
accounts Account[]
|
||||
sessions Session[]
|
||||
|
||||
@@ -2,6 +2,12 @@ import { Box, Flex, GridItem, Heading, SimpleGrid, Text, useColorModeValue } fro
|
||||
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.",
|
||||
|
||||
@@ -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 +1,98 @@
|
||||
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;
|
||||
}
|
||||
@@ -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",
|
||||
},
|
||||
|
||||
@@ -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({
|
||||
|
||||
@@ -6,7 +6,7 @@ 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";
|
||||
@@ -90,7 +90,13 @@ const RankAssistantReplies = () => {
|
||||
<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>
|
||||
</>
|
||||
);
|
||||
|
||||
@@ -4,7 +4,7 @@ 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";
|
||||
@@ -85,7 +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>
|
||||
</>
|
||||
);
|
||||
|
||||
@@ -6,7 +6,7 @@ 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";
|
||||
@@ -89,7 +89,13 @@ const RankUserReplies = () => {
|
||||
<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>
|
||||
</>
|
||||
);
|
||||
|
||||
@@ -41,9 +41,11 @@ const MessagesDashboard = () => {
|
||||
<SideMenu />
|
||||
</Box>
|
||||
<Box className="flex flex-col overflow-auto p-6 sm:pl-0 gap-14">
|
||||
<SimpleGrid columns={[1, 1, 1, 2]} spacing={2}>
|
||||
<SimpleGrid columns={[1, 1, 1, 2]} gap={4}>
|
||||
<Box>
|
||||
<Text className="text-2xl font-bold">Most recent messages</Text>
|
||||
<Text className="text-2xl font-bold" pb="4">
|
||||
Most recent messages
|
||||
</Text>
|
||||
<Box
|
||||
backgroundColor={boxBgColor}
|
||||
boxShadow="base"
|
||||
@@ -55,7 +57,9 @@ const MessagesDashboard = () => {
|
||||
</Box>
|
||||
</Box>
|
||||
<Box>
|
||||
<Text className="text-2xl font-bold">Your most recent messages</Text>
|
||||
<Text className="text-2xl font-bold" pb="4">
|
||||
Your most recent messages
|
||||
</Text>
|
||||
<Box
|
||||
backgroundColor={boxBgColor}
|
||||
boxShadow="base"
|
||||
|
||||
Vendored
+18
@@ -0,0 +1,18 @@
|
||||
import NextAuth, { DefaultSession } from "next-auth";
|
||||
import { JWT } from "next-auth/jwt";
|
||||
|
||||
declare module "next-auth" {
|
||||
interface Session {
|
||||
user: {
|
||||
/** The user's role. */
|
||||
role: string;
|
||||
} & DefaultSession["user"];
|
||||
}
|
||||
}
|
||||
|
||||
declare module "next-auth/jwt" {
|
||||
interface JWT {
|
||||
/** The user's role. */
|
||||
role?: string;
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user