Spaces:
Sleeping
Sleeping
File size: 17,379 Bytes
5fdb69e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 |
{
"cells": [
{
"cell_type": "markdown",
"id": "dfe37963-1af6-44fc-a841-8e462443f5e6",
"metadata": {},
"source": [
"## Expert Knowledge Worker\n",
"\n",
"Features:\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.\n",
"\n",
"Technology:\n",
"- RAG: LangChain\n",
"- Embedding model: OpenAIEmbeddings or HuggingFace sentence-transformers\n",
"- Encoding method: Auto-encoding\n",
"- Vector datastore: Chroma or FAISS\n",
"- Vector DB visualization: Plotly\n",
"- Dimensionality reduction technique: t-SNE\n",
"\n",
"# Dependencies"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "802137aa-8a74-45e0-a487-d1974927d7ca",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"\n",
"import os\n",
"import glob\n",
"from dotenv import load_dotenv\n",
"import gradio as gr\n",
"from langchain.document_loaders import DirectoryLoader, TextLoader\n",
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
"from langchain.schema import Document\n",
"from langchain_openai import OpenAIEmbeddings, ChatOpenAI\n",
"from langchain.embeddings import HuggingFaceEmbeddings\n",
"from langchain_chroma import Chroma\n",
"from langchain.vectorstores import FAISS\n",
"import numpy as np\n",
"from sklearn.manifold import TSNE\n",
"import plotly.graph_objects as go\n",
"from langchain.memory import ConversationBufferMemory\n",
"from langchain.chains import ConversationalRetrievalChain"
]
},
{
"cell_type": "markdown",
"id": "7187c181-5b17-4df7-b298-b7cb2b6d09f7",
"metadata": {},
"source": [
"# Setup"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "58c85082-e417-4708-9efe-81a5d55d1424",
"metadata": {},
"outputs": [],
"source": [
"MODEL = \"gpt-4o-mini\"\n",
"db_name = \"vector_db\"\n",
"db_type = \"Chroma\"\n",
"# db_type = \"FAISS\"\n",
"embed_type = \"OpenAIEmbeddings\"\n",
"# embed_type = \"sentence-transformers\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ee78efcb-60fe-449e-a944-40bab26261af",
"metadata": {},
"outputs": [],
"source": [
"# Load environment variables\n",
"\n",
"load_dotenv(override=True)\n",
"os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY')"
]
},
{
"cell_type": "markdown",
"id": "a2f0866b-5cfb-4ecd-87d1-6da872887dcd",
"metadata": {},
"source": [
"# Create Knowledge Base for RAG\n",
"\n",
"## Load Company Documents\n",
"\n",
"Uses LangChain to read in a Knowledge Base of documents and to divide up documents into overlaping chunks."
]
},
{
"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",
"text_loader_kwargs = {'encoding': 'utf-8'}\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 = RecursiveCharacterTextSplitter(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": [
"## Vector Embeddings\n",
"\n",
"Convert chunks of text into Vectors using OpenAIEmbeddings and store the Vectors in Chroma (or FAISS)."
]
},
{
"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 = None\n",
"# OpenAIEmbeddings is OpenAI's vector embedding models\n",
"if embed_type == \"OpenAIEmbeddings\":\n",
" embeddings = OpenAIEmbeddings()\n",
"\n",
"# sentence-transformers is a free Vector embeddings model from HuggingFace\n",
"elif embed_type == \"sentence-transformers\":\n",
" embeddings = HuggingFaceEmbeddings(model_name=\"sentence-transformers/all-MiniLM-L6-v2\")\n",
"\n",
"if embeddings is None:\n",
" print(\"ERROR: embeddings not set. Check embed_type is set to a valid model\")"
]
},
{
"cell_type": "markdown",
"id": "64768521-a775-472c-83c5-0c0d715d44ac",
"metadata": {},
"source": [
"## Create Vector Datastore"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "057868f6-51a6-4087-94d1-380145821550",
"metadata": {},
"outputs": [],
"source": [
"# Create vectorstore\n",
"vectorstore = None\n",
"\n",
"# Chroma is a popular open source Vector Database based on SQLLite\n",
"if db_type == \"Chroma\":\n",
" # Delete vector DB if already exists\n",
" if os.path.exists(db_name):\n",
" Chroma(persist_directory=db_name, embedding_function=embeddings).delete_collection()\n",
" \n",
" # Create vectorstore\n",
" vectorstore = Chroma.from_documents(documents=chunks, embedding=embeddings, persist_directory=db_name)\n",
" \n",
" print(f\"Vectorstore created with {vectorstore._collection.count()} documents\")\n",
"\n",
" # Get one vector and find how many dimensions it has\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\")\n",
" \n",
"# FAISS is an in-memory vector DB from Facebook\n",
"elif db_type == \"FAISS\":\n",
" # Create vectorstore\n",
" vectorstore = FAISS.from_documents(chunks, embedding=embeddings)\n",
" \n",
" total_vectors = vectorstore.index.ntotal\n",
" dimensions = vectorstore.index.d\n",
" print(f\"There are {total_vectors} vectors with {dimensions:,} dimensions in the vector store\")\n",
"\n",
"else:\n",
" print(\"ERROR: Vector datastore not created. Check db_type is set to a valid database\")"
]
},
{
"cell_type": "markdown",
"id": "b0d45462-a818-441c-b010-b85b32bcf618",
"metadata": {},
"source": [
"# Visualizing the Vector Store\n",
"\n",
"Humans are not very good at visualizing things with more than 3 dimensions so to visualize a vector datastore with thousands of dimesions. We need to use techniques like projecting down to reduce the dimensions to only 2 or 3 dimensions in a way that does the best possible job at separating things out to stay faithful to the multi-dimensional representation.\n",
"\n",
"For example, things that are far apart in these multiple dimensions will still be far apart even when projected down to 2 dimensions.\n",
"\n",
"[t-distributed stochastic neighbor embedding (t-SNE)](https://en.wikipedia.org/wiki/T-distributed_stochastic_neighbor_embedding) is a nonlinear dimensionality reduction technique for embedding high-dimensional data for visualization in a low-dimensional space of two or three dimensions.\n",
"\n",
"## Configure Visualization"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b98adf5e-d464-4bd2-9bdf-bc5b6770263b",
"metadata": {},
"outputs": [],
"source": [
"# Prework\n",
"if db_type == \"Chroma\":\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]\n",
"\n",
"elif db_type == \"FAISS\":\n",
" vectors = []\n",
" documents = []\n",
" doc_types = []\n",
" colors = []\n",
" color_map = {'products':'blue', 'employees':'green', 'contracts':'red', 'company':'orange'}\n",
" \n",
" for i in range(total_vectors):\n",
" vectors.append(vectorstore.index.reconstruct(i))\n",
" doc_id = vectorstore.index_to_docstore_id[i]\n",
" document = vectorstore.docstore.search(doc_id)\n",
" documents.append(document.page_content)\n",
" doc_type = document.metadata['doc_type']\n",
" doc_types.append(doc_type)\n",
" colors.append(color_map[doc_type])\n",
" \n",
" vectors = np.array(vectors)\n",
"\n",
"else:\n",
" print(\"ERROR: Vector datastore not created. Check db_type is set to a valid database\")"
]
},
{
"cell_type": "markdown",
"id": "bb279701-0086-44aa-a2da-14341aecf529",
"metadata": {},
"source": [
"## Reduce the dimensionality to 2D"
]
},
{
"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=f'2D {db_type} 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": "markdown",
"id": "e2b724f3-e3ad-4d42-bfa4-a89386d6414e",
"metadata": {},
"source": [
"## Reduce the dimensionality to 3D"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e1418e88-acd5-460a-bf2b-4e6efc88e3dd",
"metadata": {},
"outputs": [],
"source": [
"# 3D representation isn't as easy to navigate\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=f'3D {db_type} 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": "markdown",
"id": "9468860b-86a2-41df-af01-b2400cc985be",
"metadata": {},
"source": [
"# Expert Knowledge Worker\n",
"\n",
"Use LangChain to bring it all together by creating a conversation chain with RAG and memory.\n",
"\n",
"Key abstractions in LangChain:\n",
"- LLM: represents abstraction around a model\n",
"- Retriever: interface onto somthing like a vector store used for RAG retrieval\n",
"- Memory: represents a history of a conversation with a chatbot in memory\n",
"\n",
"Because LangChain abstracts the reprentation of the LLM, retriever and memory the code is the same for any model and knowledge base.\n",
"\n",
"Note: ok to ignore _Deprecation Warning_ for now; LangChain are not expected to remove ConversationBufferMemory any time soon.\n",
"\n",
"## Setup"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "129c7d1e-0094-4479-9459-f9360b95f244",
"metadata": {},
"outputs": [],
"source": [
"# create a new Chat with OpenAI\n",
"llm = ChatOpenAI(temperature=0.7, model_name=MODEL)\n",
"\n",
"# set up the conversation memory for the chat\n",
"memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)\n",
"\n",
"# the retriever is an abstraction over the VectorStore that will be used during RAG\n",
"retriever = vectorstore.as_retriever()\n",
"\n",
"# putting it together: set up the conversation chain with the GPT 4o-mini LLM, the vector store and memory\n",
"conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever, memory=memory)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "968e7bf2-e862-4679-a11f-6c1efb6ec8ca",
"metadata": {},
"outputs": [],
"source": [
"query = \"Can you describe Insurellm in a few sentences\"\n",
"result = conversation_chain.invoke({\"question\":query})\n",
"print(result[\"answer\"])"
]
},
{
"cell_type": "markdown",
"id": "990a2917-562c-461a-8ce9-a8ad8ad1646d",
"metadata": {},
"source": [
"## Clear Memory\n",
"\n",
"Clear the memory from the testing and restart conversation chain for UI."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e6eb99fb-33ec-4025-ab92-b634ede03647",
"metadata": {},
"outputs": [],
"source": [
"# clear the memory and restart conversation chain for UI\n",
"memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)\n",
"conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever, memory=memory)"
]
},
{
"cell_type": "markdown",
"id": "bbbcb659-13ce-47ab-8a5e-01b930494964",
"metadata": {},
"source": [
"## Functions"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c3536590-85c7-4155-bd87-ae78a1467670",
"metadata": {},
"outputs": [],
"source": [
"# Wrapping in a function - note that history isn't used, as the memory is in the conversation_chain\n",
"\n",
"def chat(message, history):\n",
" result = conversation_chain.invoke({\"question\": message})\n",
" return result[\"answer\"]"
]
},
{
"cell_type": "markdown",
"id": "b655d3da-277b-45a9-8113-747314ec0889",
"metadata": {},
"source": [
"## UI"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b252d8c1-61a8-406d-b57a-8f708a62b014",
"metadata": {},
"outputs": [],
"source": [
"# And in Gradio:\n",
"\n",
"view = gr.ChatInterface(chat, type=\"messages\", examples=[\"what is insurellm?\",\"what did avery do before?\", \"does insurellm offer any products in the auto industry space?\"], title=\"Insurellm Expert Knowledge Worker\").launch(inbrowser=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5435b2b9-935c-48cd-aaf3-73a837ecde49",
"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": "3.11.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|