From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
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.
388 lines
11 KiB
388 lines
11 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "markdown", |
|
"id": "dfe37963-1af6-44fc-a841-8e462443f5e6", |
|
"metadata": {}, |
|
"source": [ |
|
"## Expert Knowledge Worker\n", |
|
"\n", |
|
"## Extra Jupyter Notebook - Day 4.5 - switch out Chroma for FAISS!\n", |
|
"\n", |
|
"FAISS is Facebook AI Similarity Search" |
|
] |
|
}, |
|
{ |
|
"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\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", |
|
"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": "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", |
|
"documents = []\n", |
|
"for folder in folders:\n", |
|
" doc_type = os.path.basename(folder)\n", |
|
" loader = DirectoryLoader(folder, glob=\"**/*.md\", loader_cls=TextLoader)\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.\n", |
|
"\n", |
|
"More details in the resources." |
|
] |
|
}, |
|
{ |
|
"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", |
|
"# Chroma is a popular open source Vector Database based on SQLLite\n", |
|
"\n", |
|
"embeddings = OpenAIEmbeddings()\n", |
|
"\n", |
|
"# Create vectorstore\n", |
|
"\n", |
|
"# BEFORE\n", |
|
"# vectorstore = Chroma.from_documents(documents=chunks, embedding=embeddings, persist_directory=db_name)\n", |
|
"\n", |
|
"# AFTER\n", |
|
"vectorstore = FAISS.from_documents(chunks, embedding=embeddings)\n", |
|
"\n", |
|
"total_vectors = vectorstore.index.ntotal\n", |
|
"dimensions = vectorstore.index.d\n", |
|
"\n", |
|
"print(f\"There are {total_vectors} vectors with {dimensions:,} dimensions in the vector store\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "057868f6-51a6-4087-94d1-380145821550", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Prework\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)" |
|
] |
|
}, |
|
{ |
|
"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": "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 FAISS 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 FAISS 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": [ |
|
"## Time to use LangChain to bring it all together" |
|
] |
|
}, |
|
{ |
|
"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 3.5 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": "bbbcb659-13ce-47ab-8a5e-01b930494964", |
|
"metadata": {}, |
|
"source": [ |
|
"## Now we will bring this up in Gradio using the Chat interface -\n", |
|
"\n", |
|
"A quick and easy way to prototype a chat with an LLM" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "c3536590-85c7-4155-bd87-ae78a1467670", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Wrapping that in a function\n", |
|
"\n", |
|
"def chat(message, history):\n", |
|
" result = conversation_chain.invoke({\"question\": message})\n", |
|
" return result[\"answer\"]" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "b252d8c1-61a8-406d-b57a-8f708a62b014", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# And in Gradio:\n", |
|
"\n", |
|
"view = gr.ChatInterface(chat).launch()" |
|
] |
|
}, |
|
{ |
|
"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": "3.11.10" |
|
} |
|
}, |
|
"nbformat": 4, |
|
"nbformat_minor": 5 |
|
}
|
|
|