LangChain is a framework that helps you prototype LLM applications quickly. Use Arize and LangChain together to trace, evaluate, and iterate on your LLM apps and agents.

Running This Notebook

1. Step through each section below, pressing play on the code blocks to run the cells.
2. Log in your browser to the Arize App
3. Copy and paste your Arize Space ID and API key

Step 0. Install Dependencies

Install Langchain and Arize packages.

⚠️ Use a GPU to save time generating embeddings. Click on 'Runtime', select 'Change Runtime Type' and select 'GPU'.

Step 1. Setup Tracing

Copy the Arize API_KEY and SPACE_ID from your Space Settings page (shown below) to the variables in the cell below.

Step 2: Define LLM

Step 3: Test LLM Responses and Logging into Arize

Use some simple prompts to test if the LLM works properly and each prompt-response pair is logged into Arize with embeddings.

Step 4: Test LLM Chain and Agents with Arize Integration