Langchain RAG

from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_community.vectorstores import InMemoryVectorStore
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_core.documents import Document

# 1. Load documents
docs = [
    Document(page_content="LangChain is a framework for LLM apps.", metadata={}),
    Document(page_content="RAG = Retrieval Augmented Generation.", metadata={}),
]

# 2. Split documents
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
splits = splitter.split_documents(docs)

# 3. Create embeddings and store
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
vectorstore = InMemoryVectorStore.from_documents(splits, embeddings)

# 4. Create retriever
retriever = vectorstore.as_retriever(search_kwargs={"k": 4})

# 5. Use in RAG
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},
])

import { ChatOpenAI, OpenAIEmbeddings } from "@langchain/openai";
import { MemoryVectorStore } from "@langchain/classic/vectorstores/memory";
import { RecursiveCharacterTextSplitter } from "@langchain/textsplitters";
import { Document } from "@langchain/core/documents";

// 1. Load documents
const docs = [
  new Document({ pageContent: "LangChain is a framework for LLM apps.", metadata: {} }),
  new Document({ pageContent: "RAG = Retrieval Augmented Generation.", metadata: {} }),
];

// 2. Split documents
const splitter = new RecursiveCharacterTextSplitter({ chunkSize: 500, chunkOverlap: 50 });
const splits = await splitter.splitDocuments(docs);

// 3. Create embeddings and store
const embeddings = new OpenAIEmbeddings({ model: "text-embedding-3-small" });
const vectorstore = await MemoryVectorStore.fromDocuments(splits, embeddings);

// 4. Create retriever
const retriever = vectorstore.asRetriever({ k: 4 });

// 5. Use in RAG
const model = new ChatOpenAI({ model: "gpt-4.1" });
const query = "What is RAG?";
const relevantDocs = await retriever.invoke(query);

const context = relevantDocs.map(doc => doc.pageContent).join("\n\n");
const response = await model.invoke([
  { role: "system", content: `Use this context:\n\n${context}` },
  { role: "user", content: query },
]);

from langchain_community.document_loaders import PyPDFLoader

loader = PyPDFLoader("./document.pdf")
docs = loader.load()
print(f"Loaded {len(docs)} pages")

import { PDFLoader } from "@langchain/community/document_loaders/fs/pdf";

const loader = new PDFLoader("./document.pdf");
const docs = await loader.load();
console.log(`Loaded ${docs.length} pages`);

from langchain_community.document_loaders import WebBaseLoader

loader = WebBaseLoader("https://docs.langchain.com")
docs = loader.load()

import { CheerioWebBaseLoader } from "@langchain/community/document_loaders/web/cheerio";

const loader = new CheerioWebBaseLoader("https://docs.langchain.com");
const docs = await loader.load();

from langchain_community.document_loaders import DirectoryLoader, TextLoader

# Load all text files from directory
loader = DirectoryLoader(
    "path/to/documents",
    glob="**/*.txt",  # Pattern for files to load
    loader_cls=TextLoader
)
docs = loader.load()

from langchain_text_splitters import RecursiveCharacterTextSplitter

splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000,        # Characters per chunk
    chunk_overlap=200,      # Overlap for context continuity
    separators=["\n\n", "\n", " ", ""],  # Split hierarchy
)

splits = splitter.split_documents(docs)

from langchain_chroma import Chroma
from langchain_openai import OpenAIEmbeddings

vectorstore = Chroma.from_documents(
    documents=splits,
    embedding=OpenAIEmbeddings(),
    persist_directory="./chroma_db",
    collection_name="my-collection",
)

# Load existing
vectorstore = Chroma(
    persist_directory="./chroma_db",
    embedding_function=OpenAIEmbeddings(),
    collection_name="my-collection",
)

import { Chroma } from "@langchain/community/vectorstores/chroma";
import { OpenAIEmbeddings } from "@langchain/openai";

const vectorstore = await Chroma.fromDocuments(
  splits,
  new OpenAIEmbeddings(),
  { collectionName: "my-collection", url: "http://localhost:8000" }
);

from langchain_community.vectorstores import FAISS

vectorstore = FAISS.from_documents(splits, embeddings)
vectorstore.save_local("./faiss_index")

# Only load FAISS indexes that you created and fully control.
# The Python FAISS loader uses pickle-backed metadata, so never load
# downloaded, shared, or otherwise untrusted index directories.
loaded = FAISS.load_local(
    "./faiss_index",
    embeddings,
    allow_dangerous_deserialization=True,
)

import { FaissStore } from "@langchain/community/vectorstores/faiss";

const vectorstore = await FaissStore.fromDocuments(splits, embeddings);
await vectorstore.save("./faiss_index");

const loaded = await FaissStore.load("./faiss_index", embeddings);

# Basic search
results = vectorstore.similarity_search(query, k=5)

# With scores
results_with_score = vectorstore.similarity_search_with_score(query, k=5)
for doc, score in results_with_score:
    print(f"Score: {score}, Content: {doc.page_content}")

// Basic search
const results = await vectorstore.similaritySearch(query, 5);

// With scores
const resultsWithScore = await vectorstore.similaritySearchWithScore(query, 5);
for (const [doc, score] of resultsWithScore) {
  console.log(`Score: ${score}, Content: ${doc.pageContent}`);
}

# MMR balances relevance and diversity
retriever = vectorstore.as_retriever(
    search_type="mmr",
    search_kwargs={"fetch_k": 20, "lambda_mult": 0.5, "k": 5},
)

# Add metadata when creating documents
docs = [
    Document(
        page_content="Python programming guide",
        metadata={"language": "python", "topic": "programming"}
    ),
]

# Search with filter
results = vectorstore.similarity_search(
    "programming",
    k=5,
    filter={"language": "python"}  # Only Python docs
)

from langchain.agents import create_agent
from langchain.tools import tool

@tool
def search_docs(query: str) -> str:
    """Search documentation for relevant information."""
    docs = retriever.invoke(query)
    return "\n\n".join([d.page_content for d in docs])

agent = create_agent(
    model="gpt-4.1",
    tools=[search_docs],
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "How do I create an agent?"}]
})

import { createAgent } from "langchain";
import { tool } from "@langchain/core/tools";
import { z } from "zod";

const searchDocs = tool(
  async (input) => {
    const docs = await retriever.invoke(input.query);
    return docs.map(d => d.pageContent).join("\n\n");
  },
  {
    name: "search_docs",
    description: "Search documentation for relevant information.",
    schema: z.object({ query: z.string() }),
  }
);

const agent = createAgent({
  model: "gpt-4.1",
  tools: [searchDocs],
});

const result = await agent.invoke({
  messages: [{ role: "user", content: "How do I create an agent?" }],
});