langchain data connections

data_connections/us_constitution_assistant.ipynb

@@ -0,0 +1,143 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "925794f5-a4a8-4753-86b9-8fe4dac8455e",
+   "metadata": {},
+   "source": [
+    "## Ask a Legal Research Assistant Bot about the US Constitution"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "063dcd9d-b508-499d-a23e-efa892bb628a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.vectorstores import Chroma\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.document_loaders import TextLoader\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.retrievers import ContextualCompressionRetriever\n",
+    "from langchain.retrievers.document_compressors import LLMChainExtractor"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "77afad7d-9c48-44f8-878e-46fc10f4c804",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def us_constitution_helper(question):\n",
+    "    \"\"\"\n",
+    "    Takes in a question about the US Constitution and returns the most relevant\n",
+    "    part of the constitution. Notice it may not directly answer the actual question!\n",
+    "    \"\"\"\n",
+    "\n",
+    "    loader = TextLoader(\"US_Constitution.txt\")\n",
+    "    documents = loader.load()\n",
+    "\n",
+    "    text_splitter = CharacterTextSplitter.from_tiktoken_encoder(chunk_size=500)\n",
+    "    docs = text_splitter.split_documents(documents)\n",
+    "\n",
+    "    embedding_function = OpenAIEmbeddings()\n",
+    "    db = Chroma.from_documents(docs, embedding_function, persist_directory=\"./constitution\")\n",
+    "    db.persist()\n",
+    "\n",
+    "    llm = ChatOpenAI(temperature=0)\n",
+    "    compressor = LLMChainExtractor.from_llm(llm)\n",
+    "    compression_retriever = ContextualCompressionRetriever(base_compressor=compressor,\n",
+    "                                                            base_retriever=db.as_retriever())\n",
+    "\n",
+    "    compressed_docs = compression_retriever.get_relevant_documents(question)\n",
+    "\n",
+    "    return compressed_docs[0].page_content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "072ef3e4-49d5-48c7-9882-57100401ba35",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/yudhvir/Documents/miniconda3/envs/nlp/lib/python3.11/site-packages/langchain/chains/llm.py:275: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Fifth Amendment\n",
+      "No person shall be held to answer for a capital, or otherwise infamous crime, unless on a presentment or indictment of a Grand Jury, except in cases arising in the land or naval forces, or in the Militia, when in actual service in time of War or public danger; nor shall any person be subject for the same offence to be twice put in jeopardy of life or limb; nor shall be compelled in any criminal case to be a witness against himself, nor be deprived of life, liberty, or property, without due process of law; nor shall private property be taken for public use, without just compensation.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(us_constitution_helper(\"What is the 5th Amendment?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e051813e-3329-4880-ae1f-7500cb6d3bb8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/yudhvir/Documents/miniconda3/envs/nlp/lib/python3.11/site-packages/langchain/chains/llm.py:275: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The powers not delegated to the United States by the Constitution, nor prohibited by it to the States, are reserved to the States respectively, or to the people.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(us_constitution_helper(\"What is the 10th Amendment?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "df35b64a-6323-44a6-a076-29f7a3cbdb18",
+   "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": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}