langchain[minor]: Adding infinity embedding integration. (#13928)

This adds integation to https://github.com/michaelfeil/infinity. Users requested it in michaelfeil/infinity#36 @saatvikshah Follows my implementation of gradient.ai. Feedback 1: Well done - I love your CI / repo / poetry setup - I adapted a lot in https://github.com/michaelfeil/infinity. Feedback 2: Not so good: The openai integration contains to much reverse engineering - in general projects such as michaelfeil/infinity and huggingface/text-embeddings-inference are compatible to the `pip install openai` package. Reverse engineering like this one is really hindering the use for me: https://github.com/langchain-ai/langchain/blob/8e88ba16a88affc272da4bb99bd515b714781179/libs/langchain/langchain/embeddings/openai.py#L347 https://github.com/langchain-ai/langchain/blob/8e88ba16a88affc272da4bb99bd515b714781179/libs/langchain/langchain/embeddings/openai.py#L351 - it is about preventing 3rd party providers to use the same url + uses interfaces of openai, that are not publically documented.
langchain-ai · Nov 28, 2023 · 6861626 · 6861626
1 parent 10a6e7c
commit 6861626
Show file tree

Hide file tree

Showing 6 changed files with 629 additions and 0 deletions.
diff --git a/docs/docs/integrations/providers/infinity.mdx b/docs/docs/integrations/providers/infinity.mdx
@@ -0,0 +1,11 @@
+# Infinity
+
+>[Infinity](https://github.com/michaelfeil/infinity) allows the creation of text embeddings.
+
+## Text Embedding Model
+
+There exists an infinity Embedding model, which you can access with 
+```python
+from langchain.embeddings import InfinityEmbeddings
+```
+For a more detailed walkthrough of this, see [this notebook](/docs/integrations/text_embedding/infinity)
diff --git a/docs/docs/integrations/text_embedding/infinity.ipynb b/docs/docs/integrations/text_embedding/infinity.ipynb
@@ -0,0 +1,191 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Infinity\n",
+    "\n",
+    "`Infinity` allows to create `Embeddings` using a MIT-licensed Embedding Server. \n",
+    "\n",
+    "This notebook goes over how to use Langchain with Embeddings with the [Infinity Github Project](https://github.com/michaelfeil/infinity).\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import InfinityEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Optional: Make sure to start the Infinity instance\n",
+    "\n",
+    "To install infinity use the following command. For further details check out the [Docs on Github](https://github.com/michaelfeil/infinity).\n",
+    "```bash\n",
+    "pip install infinity_emb[all]\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: infinity_emb[cli] in /home/michi/langchain/.venv/lib/python3.10/site-packages (0.0.8)\n",
+      "\u001b[33mWARNING: infinity-emb 0.0.8 does not provide the extra 'cli'\u001b[0m\u001b[33m\n",
+      "\u001b[0mRequirement already satisfied: numpy>=1.20.0 in /home/michi/langchain/.venv/lib/python3.10/site-packages (from infinity_emb[cli]) (1.24.4)\n",
+      "\u001b[33mWARNING: There was an error checking the latest version of pip.\u001b[0m\u001b[33m\n",
+      "\u001b[0m"
+     ]
+    }
+   ],
+   "source": [
+    "# Install the infinity package\n",
+    "!pip install infinity_emb[cli,torch]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Start up the server - best to be done from a separate terminal, not inside Jupyter Notebook\n",
+    "\n",
+    "```bash\n",
+    "model=sentence-transformers/all-MiniLM-L6-v2\n",
+    "port=7797\n",
+    "infinity_emb --port $port --model-name-or-path $model\n",
+    "```\n",
+    "\n",
+    "or alternativley just use docker:\n",
+    "```bash\n",
+    "model=sentence-transformers/all-MiniLM-L6-v2\n",
+    "port=7797\n",
+    "docker run -it --gpus all -p $port:$port michaelf34/infinity:latest --model-name-or-path $model --port $port\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Embed your documents using your Infinity instance "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "documents = [\n",
+    "    \"Baguette is a dish.\",\n",
+    "    \"Paris is the capital of France.\",\n",
+    "    \"numpy is a lib for linear algebra\",\n",
+    "    \"You escaped what I've escaped - You'd be in Paris getting fucked up too\",\n",
+    "]\n",
+    "query = \"Where is Paris?\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "embeddings created successful\n"
+     ]
+    }
+   ],
+   "source": [
+    "#\n",
+    "infinity_api_url = \"http://localhost:7797/v1\"\n",
+    "# model is currently not validated.\n",
+    "embeddings = InfinityEmbeddings(\n",
+    "    model=\"sentence-transformers/all-MiniLM-L6-v2\", infinity_api_url=infinity_api_url\n",
+    ")\n",
+    "try:\n",
+    "    documents_embedded = embeddings.embed_documents(documents)\n",
+    "    query_result = embeddings.embed_query(query)\n",
+    "    print(\"embeddings created successful\")\n",
+    "except Exception as ex:\n",
+    "    print(\n",
+    "        \"Make sure the infinity instance is running. Verify by clicking on \"\n",
+    "        f\"{infinity_api_url.replace('v1','docs')} Exception: {ex}. \"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'Baguette is a dish.': 0.31344215908661155,\n",
+       " 'Paris is the capital of France.': 0.8148670296896388,\n",
+       " 'numpy is a lib for linear algebra': 0.004429399861302009,\n",
+       " \"You escaped what I've escaped - You'd be in Paris getting fucked up too\": 0.5088476180154582}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# (demo) compute similarity\n",
+    "import numpy as np\n",
+    "\n",
+    "scores = np.array(documents_embedded) @ np.array(query_result).T\n",
+    "dict(zip(documents, scores))"
+   ]
+  }
+ ],
+ "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": "3.10.12"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/libs/langchain/langchain/embeddings/__init__.py b/libs/langchain/langchain/embeddings/__init__.py
@@ -43,6 +43,7 @@
     HuggingFaceInstructEmbeddings,
 )
 from langchain.embeddings.huggingface_hub import HuggingFaceHubEmbeddings
+from langchain.embeddings.infinity import InfinityEmbeddings
 from langchain.embeddings.javelin_ai_gateway import JavelinAIGatewayEmbeddings
 from langchain.embeddings.jina import JinaEmbeddings
 from langchain.embeddings.johnsnowlabs import JohnSnowLabsEmbeddings
@@ -81,6 +82,7 @@
     "FastEmbedEmbeddings",
     "HuggingFaceEmbeddings",
     "HuggingFaceInferenceAPIEmbeddings",
+    "InfinityEmbeddings",
     "GradientEmbeddings",
     "JinaEmbeddings",
     "LlamaCppEmbeddings",