Add files via upload

Ollama/Self_Querying DEMO.ipynb

@@ -0,0 +1,224 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Advanced RAG: Self-querying\n",
+    "\n",
+    "### Before doing anything\n",
+    "\n",
+    "### Ollama Running in background\n",
+    "\n",
+    "- [ollama pull nomic-embed-text](https://ollama.com/library/nomic-embed-text)\n",
+    "- [ollama run qwen2](https://ollama.com/library/qwen2)\n",
+    "\n",
+    "### Install these packages\n",
+    "\n",
+    "- `!pip install ollama`\n",
+    "- `!pip install langchain`\n",
+    "- `!pip install --upgrade --quiet lark langchain-chroma`\n",
+    "- `!pip install langchain_community`\n",
+    "\n",
+    "________________________________________________________________________________"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Prepare Documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_chroma import Chroma\n",
+    "from langchain_core.documents import Document\n",
+    "from langchain_community.embeddings import OllamaEmbeddings\n",
+    "\n",
+    "# You can make document from different loaders (e.g PDF, HTML, JSON, etc.)\n",
+    "# different loaders here: https://python.langchain.com/v0.1/docs/modules/data_connection/document_loaders/\n",
+    "\n",
+    "\n",
+    "docs = [\n",
+    "    Document(\n",
+    "        page_content=\"A bunch of scientists bring back dinosaurs and mayhem breaks loose\",\n",
+    "        metadata={\"year\": 1993, \"rating\": 7.7, \"genre\": \"science fiction\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"Leo DiCaprio gets lost in a dream within a dream within a dream within a ...\",\n",
+    "        metadata={\"year\": 2010, \"director\": \"Christopher Nolan\", \"rating\": 8.2},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea\",\n",
+    "        metadata={\"year\": 2006, \"director\": \"Satoshi Kon\", \"rating\": 8.6},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\",\n",
+    "        metadata={\"year\": 2019, \"director\": \"Greta Gerwig\", \"rating\": 8.3},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"Toys come alive and have a blast doing so\",\n",
+    "        metadata={\"year\": 1995, \"genre\": \"animated\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"Three men walk into the Zone, three men walk out of the Zone\",\n",
+    "        metadata={\n",
+    "            \"year\": 1979,\n",
+    "            \"director\": \"Andrei Tarkovsky\",\n",
+    "            \"genre\": \"thriller\",\n",
+    "            \"rating\": 9.9,\n",
+    "        },\n",
+    "    ),\n",
+    "]\n",
+    "vectorstore = Chroma.from_documents(docs, OllamaEmbeddings(model=\"nomic-embed-text\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Creating our self-querying retriever"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains.query_constructor.base import AttributeInfo\n",
+    "from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
+    "\n",
+    "\n",
+    "metadata_field_info = [\n",
+    "    AttributeInfo(\n",
+    "        name=\"genre\",\n",
+    "        description=\"The genre of the movie. One of ['science fiction', 'comedy', 'drama', 'thriller', 'romance', 'action', 'animated']\",\n",
+    "        type=\"string\",\n",
+    "    ),\n",
+    "       AttributeInfo(\n",
+    "        name=\"year\", #name=\"email\",\n",
+    "        description=\"The year the movie was released\",\n",
+    "        type=\"integer\",\n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"director\", # eg. name=\"purchase_history\"\n",
+    "        description=\"The name of the movie director\",\n",
+    "        type=\"string\",\n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"rating\", description=\"A 1-10 rating for the movie\", type=\"float\"\n",
+    "    ),\n",
+    "    \n",
+    "]\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_models import ChatOllama\n",
+    "\n",
+    "document_content_description = \"Brief summary of a movie\"\n",
+    "\n",
+    "llm = ChatOllama(model=\"qwen2\",temperature=0)\n",
+    "\n",
+    "retriever = SelfQueryRetriever.from_llm(\n",
+    "    llm,\n",
+    "    vectorstore,\n",
+    "    document_content_description,\n",
+    "    metadata_field_info,\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Query"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'director': 'Satoshi Kon', 'rating': 8.6, 'year': 2006}),\n",
+       " Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'director': 'Andrei Tarkovsky', 'genre': 'thriller', 'rating': 9.9, 'year': 1979})]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# This example only specifies a filter\n",
+    "retriever.invoke(\"I want to watch a movie rated higher than 8.5\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Toys come alive and have a blast doing so', metadata={'genre': 'animated', 'year': 1995}),\n",
+       " Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'genre': 'science fiction', 'rating': 7.7, 'year': 1993}),\n",
+       " Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'director': 'Satoshi Kon', 'rating': 8.6, 'year': 2006}),\n",
+       " Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'director': 'Greta Gerwig', 'rating': 8.3, 'year': 2019})]"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# This example specifies a query and a filter\n",
+    "retriever.invoke(\"is there a movie about toys\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "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": "3.1.undefined"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}