You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 

337 lines
10 KiB

{
"cells": [
{
"cell_type": "markdown",
"id": "dfe37963-1af6-44fc-a841-8e462443f5e6",
"metadata": {},
"source": [
"## Expert Knowledge Worker\n",
"\n",
"### A question answering agent that is an expert knowledge worker\n",
"### To be used by employees of Insurellm, an Insurance Tech company\n",
"### The agent needs to be accurate and the solution should be low cost.\n",
"\n",
"This project will use RAG (Retrieval Augmented Generation) to ensure our question/answering assistant has high accuracy."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ba2779af-84ef-4227-9e9e-6eaf0df87e77",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"\n",
"import os\n",
"import glob\n",
"from dotenv import load_dotenv\n",
"import gradio as gr"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "802137aa-8a74-45e0-a487-d1974927d7ca",
"metadata": {},
"outputs": [],
"source": [
"# imports for langchain and Chroma and plotly\n",
"\n",
"from langchain.document_loaders import DirectoryLoader, TextLoader\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.schema import Document\n",
"from langchain_openai import OpenAIEmbeddings, ChatOpenAI\n",
"from langchain_chroma import Chroma\n",
"import numpy as np\n",
"from sklearn.manifold import TSNE\n",
"import plotly.graph_objects as go"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "58c85082-e417-4708-9efe-81a5d55d1424",
"metadata": {},
"outputs": [],
"source": [
"# price is a factor for our company, so we're going to use a low cost model\n",
"\n",
"MODEL = \"gpt-4o-mini\"\n",
"db_name = \"vector_db\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ee78efcb-60fe-449e-a944-40bab26261af",
"metadata": {},
"outputs": [],
"source": [
"# Load environment variables in a file called .env\n",
"\n",
"load_dotenv()\n",
"os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY', 'your-key-if-not-using-env')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "730711a9-6ffe-4eee-8f48-d6cfb7314905",
"metadata": {},
"outputs": [],
"source": [
"# Read in documents using LangChain's loaders\n",
"# Take everything in all the sub-folders of our knowledgebase\n",
"\n",
"folders = glob.glob(\"knowledge-base/*\")\n",
"\n",
"# With thanks to Jon R, a student on the course, for this fix needed for some users \n",
"text_loader_kwargs={'autodetect_encoding': True}\n",
"\n",
"documents = []\n",
"for folder in folders:\n",
" doc_type = os.path.basename(folder)\n",
" loader = DirectoryLoader(folder, glob=\"**/*.md\", loader_cls=TextLoader, loader_kwargs=text_loader_kwargs)\n",
" folder_docs = loader.load()\n",
" for doc in folder_docs:\n",
" doc.metadata[\"doc_type\"] = doc_type\n",
" documents.append(doc)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7310c9c8-03c1-4efc-a104-5e89aec6db1a",
"metadata": {},
"outputs": [],
"source": [
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\n",
"chunks = text_splitter.split_documents(documents)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cd06e02f-6d9b-44cc-a43d-e1faa8acc7bb",
"metadata": {},
"outputs": [],
"source": [
"len(chunks)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2c54b4b6-06da-463d-bee7-4dd456c2b887",
"metadata": {},
"outputs": [],
"source": [
"doc_types = set(chunk.metadata['doc_type'] for chunk in chunks)\n",
"print(f\"Document types found: {', '.join(doc_types)}\")"
]
},
{
"cell_type": "markdown",
"id": "77f7d2a6-ccfa-425b-a1c3-5e55b23bd013",
"metadata": {},
"source": [
"## A sidenote on Embeddings, and \"Auto-Encoding LLMs\"\n",
"\n",
"We will be mapping each chunk of text into a Vector that represents the meaning of the text, known as an embedding.\n",
"\n",
"OpenAI offers a model to do this, which we will use by calling their API with some LangChain code.\n",
"\n",
"This model is an example of an \"Auto-Encoding LLM\" which generates an output given a complete input.\n",
"It's different to all the other LLMs we've discussed today, which are known as \"Auto-Regressive LLMs\", and generate future tokens based only on past context.\n",
"\n",
"Another example of an Auto-Encoding LLMs is BERT from Google. In addition to embedding, Auto-encoding LLMs are often used for classification."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "78998399-ac17-4e28-b15f-0b5f51e6ee23",
"metadata": {},
"outputs": [],
"source": [
"# Put the chunks of data into a Vector Store that associates a Vector Embedding with each chunk\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "763e51ff-5787-4a56-8176-36b7c5796fe3",
"metadata": {},
"outputs": [],
"source": [
"# Check if a Chroma Datastore already exists - if so, delete the collection to start from scratch\n",
"\n",
"if os.path.exists(db_name):\n",
" Chroma(persist_directory=db_name, embedding_function=embeddings).delete_collection()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "99fe3a37-480f-4d55-be48-120588d5846b",
"metadata": {},
"outputs": [],
"source": [
"# Create our Chroma vectorstore!\n",
"\n",
"vectorstore = Chroma.from_documents(documents=chunks, embedding=embeddings, persist_directory=db_name)\n",
"print(f\"Vectorstore created with {vectorstore._collection.count()} documents\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "057868f6-51a6-4087-94d1-380145821550",
"metadata": {},
"outputs": [],
"source": [
"# Get one vector and find how many dimensions it has\n",
"\n",
"collection = vectorstore._collection\n",
"sample_embedding = collection.get(limit=1, include=[\"embeddings\"])[\"embeddings\"][0]\n",
"dimensions = len(sample_embedding)\n",
"print(f\"The vectors have {dimensions:,} dimensions\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "61e393a0-dd4c-419f-842f-60c1cb3b716b",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"id": "b0d45462-a818-441c-b010-b85b32bcf618",
"metadata": {},
"source": [
"## Visualizing the Vector Store\n",
"\n",
"Let's take a minute to look at the documents and their embedding vectors to see what's going on."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b98adf5e-d464-4bd2-9bdf-bc5b6770263b",
"metadata": {},
"outputs": [],
"source": [
"# Prework\n",
"\n",
"result = collection.get(include=['embeddings', 'documents', 'metadatas'])\n",
"vectors = np.array(result['embeddings'])\n",
"documents = result['documents']\n",
"doc_types = [metadata['doc_type'] for metadata in result['metadatas']]\n",
"colors = [['blue', 'green', 'red', 'orange'][['products', 'employees', 'contracts', 'company'].index(t)] for t in doc_types]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "427149d5-e5d8-4abd-bb6f-7ef0333cca21",
"metadata": {},
"outputs": [],
"source": [
"# We humans find it easier to visalize things in 2D!\n",
"# Reduce the dimensionality of the vectors to 2D using t-SNE\n",
"# (t-distributed stochastic neighbor embedding)\n",
"\n",
"tsne = TSNE(n_components=2, random_state=42)\n",
"reduced_vectors = tsne.fit_transform(vectors)\n",
"\n",
"# Create the 2D scatter plot\n",
"fig = go.Figure(data=[go.Scatter(\n",
" x=reduced_vectors[:, 0],\n",
" y=reduced_vectors[:, 1],\n",
" mode='markers',\n",
" marker=dict(size=5, color=colors, opacity=0.8),\n",
" text=[f\"Type: {t}<br>Text: {d[:100]}...\" for t, d in zip(doc_types, documents)],\n",
" hoverinfo='text'\n",
")])\n",
"\n",
"fig.update_layout(\n",
" title='2D Chroma Vector Store Visualization',\n",
" scene=dict(xaxis_title='x',yaxis_title='y'),\n",
" width=800,\n",
" height=600,\n",
" margin=dict(r=20, b=10, l=10, t=40)\n",
")\n",
"\n",
"fig.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e1418e88-acd5-460a-bf2b-4e6efc88e3dd",
"metadata": {},
"outputs": [],
"source": [
"# Let's try 3D!\n",
"\n",
"tsne = TSNE(n_components=3, random_state=42)\n",
"reduced_vectors = tsne.fit_transform(vectors)\n",
"\n",
"# Create the 3D scatter plot\n",
"fig = go.Figure(data=[go.Scatter3d(\n",
" x=reduced_vectors[:, 0],\n",
" y=reduced_vectors[:, 1],\n",
" z=reduced_vectors[:, 2],\n",
" mode='markers',\n",
" marker=dict(size=5, color=colors, opacity=0.8),\n",
" text=[f\"Type: {t}<br>Text: {d[:100]}...\" for t, d in zip(doc_types, documents)],\n",
" hoverinfo='text'\n",
")])\n",
"\n",
"fig.update_layout(\n",
" title='3D Chroma Vector Store Visualization',\n",
" scene=dict(xaxis_title='x', yaxis_title='y', zaxis_title='z'),\n",
" width=900,\n",
" height=700,\n",
" margin=dict(r=20, b=10, l=10, t=40)\n",
")\n",
"\n",
"fig.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9b3ada26-b4b7-42fc-b943-933c14adf89b",
"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": "3.11.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}