> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langtrace.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Langchain

> Langtrace and Langchain Integration Guide

Langtrace integrates directly with Langchain, offering detailed, real-time insights into performance metrics such as cost, token usage, accuracy, and latency.

## Setup

1. Install Langtrace's SDK and [initialize](/quickstart) the SDK in your code.

*Note: You'll need API key from Langtrace. Sign up for [Langtrace](https://langtrace.ai) if you haven't done so already.*

```bash Python theme={null}
# Install the SDK
pip install -U langtrace-python-sdk langchain langchain-chroma langchainhub

```

```bash Typescript theme={null}
npm install @pinecone-database/pinecone-client
```

2. Setup environment variables:

```bash Shell theme={null}
export LANGTRACE_API_KEY=YOUR_LANGTRACE_API_KEY
export OPENAI_API_KEY=YOUR_OPENAI_API_KEY
```

## Usage

Generate a simple output with your deployment's model:

<CodeGroup>
  ```python Python theme={null}
  import os
  from langtrace_python_sdk import langtrace # Must precede any llm module imports
  langtrace.init(api_key = os.environ['LANGTRACE_API_KEY'])
  from langchain_openai import ChatOpenAI

  llm = ChatOpenAI(model="gpt-3.5-turbo-0125")

  import bs4
  from langchain import hub
  from langchain_chroma import Chroma
  from langchain_community.document_loaders import TextLoader
  from langchain_core.output_parsers import StrOutputParser
  from langchain_core.runnables import RunnablePassthrough
  from langchain_openai import OpenAIEmbeddings
  from langchain_text_splitters import RecursiveCharacterTextSplitter

  ```
</CodeGroup>

Create a vector store index and query it

<CodeGroup>
  ```python python theme={null}
  # We will be loading a document from the assets folder to create embeddings and query it

  loader = TextLoader("assets/soccer_rules.txt")
  docs = loader.load()
  text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
  splits = text_splitter.split_documents(docs)
  vectorstore = Chroma.from_documents(documents=splits, embedding=OpenAIEmbeddings())

  # Retrieve and generate using the relevant snippets of the blog.
  retriever = vectorstore.as_retriever()
  prompt = hub.pull("rlm/rag-prompt")

  ```
</CodeGroup>

Retrieve and generate using the relevant snippets of the document.

<CodeGroup>
  ```python Python theme={null}
  retriever = vectorstore.as_retriever()
  prompt = hub.pull("rlm/rag-prompt")
  ```
</CodeGroup>

Format our document ,setup a rag chain and query

<CodeGroup>
  ```python Python theme={null}
    def format_docs(docs):
      return "\n\n".join(doc.page_content for doc in docs)


  rag_chain = (
      {"context": retriever | format_docs, "question": RunnablePassthrough()}
      | prompt
      | llm
      | StrOutputParser()
  )

  rag_chain.invoke("What is Offside??")
  ```
</CodeGroup>

You can now view your traces on the Langtrace dashboard

<img src="https://mintcdn.com/langtraceai-2/m7BVnnhK3Cx2yRxS/images/langchain.png?fit=max&auto=format&n=m7BVnnhK3Cx2yRxS&q=85&s=1eaa5ae9eb4bc25bad88fa696ab4b3be" alt="traces" width="1710" height="834" data-path="images/langchain.png" />

Want to see more supported methods? Checkout the sample code in the [Langtrace Langchain Python Example](https://python.langchain.com/docs/get_started/installation/)