langchain-rag

Pipeline: Key Components: docs = [ Document(page_content="LangChain is a framework for LLM apps.", metadata={}), Document(page_content="RAG = Retrieval Augmented Generation.", metadata={}), ] splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50) splits = splitter.split_documents(docs) embeddings = OpenAIEmbeddings(model="text-embedding-3-small") vectorstore = InMemoryVectorStore.from_documents(splits, embeddings) retriever = vectorstore.as_retriever(search_kwargs={"k": 4}) model = ChatOpenAI(model="gpt-4.1") query = "What is RAG?" relevant_docs = retriever.invoke(query) context = "\n\n".join([doc.page_content for doc in relevant_docs]) response = model.invoke([ {"role": "system", "content": f"Use this context:\n\n{context}"}, {"role": "user", "content": query}, ]) loader = PyPDFLoader("./document.pdf") docs = loader.load() print(f"Loaded {len(docs)} pages") loader = WebBaseLoader(" ") docs = loader.load() loader = DirectoryLoader( "path/to/documents", glob="**/*.txt", # Pattern for files to load loader_cls=TextLoader ) docs = loader.load() vectorstore = Chroma.from_documents( documents=splits, embedding=OpenAIEmbeddings(), persist_directory="./chroma_db", collection_name="my-collection", ) vectorstore = Chroma( persist_directory="./chroma_db", embedding_function=OpenAIEmbeddings(), collection_name="my-collection", ) vectorstore =...