Add example demonstrating using openai & cohere embeddings

examples/alternative_embeddings.ipynb

@@ -0,0 +1,205 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        " # Alternative Embeddings\n",
+        " \n",
+        " This notebook demonstrates how to use alternative embedding functions.\n",
+        " "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import chromadb"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "Using embedded DuckDB without persistence: data will be transient\n"
+          ]
+        }
+      ],
+      "source": [
+        "client = chromadb.Client()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from chromadb.utils import embedding_functions"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Using OpenAI Embeddings. This assumes you have the openai package installed\n",
+        "openai_ef = embedding_functions.OpenAIEmbeddingFunction(\n",
+        "    api_key=\"OPENAI_API_KEY\", # Replace with your own OpenAI API key\n",
+        "    model_name=\"text-embedding-ada-002\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Create a new chroma collection\n",
+        "openai_collection = client.create_collection(name=\"openai_embeddings\", embedding_function=openai_ef)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "openai_collection.add(\n",
+        "    documents=[\"This is a document\", \"This is another document\"],\n",
+        "    metadatas=[{\"source\": \"my_source\"}, {\"source\": \"my_source\"}],\n",
+        "    ids=[\"id1\", \"id2\"]\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "{'ids': [['id1', 'id2']],\n",
+              " 'embeddings': None,\n",
+              " 'documents': [['This is a document', 'This is another document']],\n",
+              " 'metadatas': [[{'source': 'my_source'}, {'source': 'my_source'}]],\n",
+              " 'distances': [[0.13865342736244202, 0.20187020301818848]]}"
+            ]
+          },
+          "execution_count": 8,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "results = openai_collection.query(\n",
+        "    query_texts=[\"This is a query document\"],\n",
+        "    n_results=2\n",
+        ")\n",
+        "results"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Using Cohere Embeddings. This assumes you have the cohere package installed\n",
+        "cohere_ef  = embedding_functions.CohereEmbeddingFunction(\n",
+        "    api_key=\"COHERE_API_KEY\",  \n",
+        "    model_name=\"large\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 10,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Create a new chroma collection\n",
+        "cohere_collection = client.create_collection(name=\"cohere_embeddings\", embedding_function=cohere_ef)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 11,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "cohere_collection.add(\n",
+        "    documents=[\"This is a document\", \"This is another document\"],\n",
+        "    metadatas=[{\"source\": \"my_source\"}, {\"source\": \"my_source\"}],\n",
+        "    ids=[\"id1\", \"id2\"]\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 12,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "{'ids': [['id1', 'id2']],\n",
+              " 'embeddings': None,\n",
+              " 'documents': [['This is a document', 'This is another document']],\n",
+              " 'metadatas': [[{'source': 'my_source'}, {'source': 'my_source'}]],\n",
+              " 'distances': [[4343.1328125, 5653.28759765625]]}"
+            ]
+          },
+          "execution_count": 12,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "results = cohere_collection.query(\n",
+        "    query_texts=[\"This is a query document\"],\n",
+        "    n_results=2\n",
+        ")\n",
+        "results"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3 (ipykernel)",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.9.13"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}