Tensorlake can be used with Langchain in two ways:
  1. Using the Python SDK tensorlake to upload files and parse them.
  2. Using the langchain-tensorlake package as a tool in LangGraph agents.

​
Using the Langchain Tool

The lanchain-tensorlake package provides a tool that can be used in LangGraph agents. This enables your agents to automatically use Tensorlake for Document Parsing, without having to write any code to parse the documents.

​
1. Install the Langchain Tool

pip install langchain-tensorlake langgraph langchain-openai

​
2. Setup the Environment

export TENSORLAKE_API_KEY="your-tensorlake-api-key"
export OPENAI_API_KEY = "your-openai-api-key"

​
3. Use the Tool

from langchain_tensorlake import DocumentParserOptions, document_markdown_tool
from langgraph.prebuilt import create_react_agent

agent = create_react_agent(
    model="openai:gpt-4o-mini",
    tools=[document_markdown_tool],
    name="financial-analyst",
)

result = agent.invoke({"messages": [{"role": "user", "content": "What is the quarterly revenue of Apple based on this file? https://www.apple.com/newsroom/pdfs/fy2025-q2/FY25_Q2_Consolidated_Financial_Statements.pdf"}]})