From 3cd271d8d7d3619ff9ae436ac9be24bb134554cb Mon Sep 17 00:00:00 2001
From: Thomas Lemoine <lemoine123thomas@gmail.com>
Date: Fri, 24 Mar 2023 17:01:18 -0400
Subject: [PATCH] introducing pinecone stuff

---
 requirements.txt  |   3 +-
 src/testing.ipynb | 153 +++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 154 insertions(+), 2 deletions(-)

diff --git a/requirements.txt b/requirements.txt
index db82262..833d9ac 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -3,4 +3,5 @@ openai
 numpy
 langchain
 requests
-tiktoken
\ No newline at end of file
+tiktoken
+pinecone
\ No newline at end of file
diff --git a/src/testing.ipynb b/src/testing.ipynb
index 54a561b..21eae06 100644
--- a/src/testing.ipynb
+++ b/src/testing.ipynb
@@ -1305,6 +1305,157 @@
     "limited_text = limit_tokens(input_text, 1000)\n",
     "print(limited_text)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pinecone\n",
+    "import config\n",
+    "PINECONE_API_KEY = config.PINECONE_API_KEY\n",
+    "\n",
+    "pinecone.init(api_key=PINECONE_API_KEY, environment=\"us-central1-gcp\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['quickstart']"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\n",
+    "pinecone.create_index(\"quickstart\", dimension=8, metric=\"euclidean\", pod_type=\"p1\")\n",
+    "pinecone.list_indexes()\n",
+    "# Returns:\n",
+    "# ['quickstart']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "index = pinecone.Index(\"quickstart\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'upserted_count': 5}"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Upsert sample data (5 8-dimensional vectors)\n",
+    "index.upsert([\n",
+    "    (\"A\", [0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1]),\n",
+    "    (\"B\", [0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2]),\n",
+    "    (\"C\", [0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3]),\n",
+    "    (\"D\", [0.4, 0.4, 0.4, 0.4, 0.4, 0.4, 0.4, 0.4]),\n",
+    "    (\"E\", [0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5])\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'dimension': 8,\n",
+       " 'index_fullness': 0.0,\n",
+       " 'namespaces': {'': {'vector_count': 5}},\n",
+       " 'total_vector_count': 5}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "index.describe_index_stats()\n",
+    "# Returns:\n",
+    "# {'dimension': 8, 'index_fullness': 0.0, 'namespaces': {'': {'vector_count': 5}}}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'matches': [{'id': 'C',\n",
+       "              'score': 0.0,\n",
+       "              'values': [0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3]},\n",
+       "             {'id': 'D',\n",
+       "              'score': 0.0799999237,\n",
+       "              'values': [0.4, 0.4, 0.4, 0.4, 0.4, 0.4, 0.4, 0.4]},\n",
+       "             {'id': 'B',\n",
+       "              'score': 0.0800000429,\n",
+       "              'values': [0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2]}],\n",
+       " 'namespace': ''}"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "index.query(\n",
+    "  vector=[0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3],\n",
+    "  top_k=3,\n",
+    "  include_values=True\n",
+    ")\n",
+    "# Returns:\n",
+    "# {'matches': [{'id': 'C',\n",
+    "#               'score': 0.0,\n",
+    "#               'values': [0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3]},\n",
+    "#              {'id': 'D',\n",
+    "#               'score': 0.0799999237,\n",
+    "#               'values': [0.4, 0.4, 0.4, 0.4, 0.4, 0.4, 0.4, 0.4]},\n",
+    "#              {'id': 'B',\n",
+    "#               'score': 0.0800000429,\n",
+    "#               'values': [0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2]}],\n",
+    "#  'namespace': ''}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pinecone.delete_index(\"quickstart\")"
+   ]
   }
  ],
  "metadata": {
@@ -1323,7 +1474,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.10.7"
   },
   "orig_nbformat": 4,
   "vscode": {