--- title: "Vercel AI SDK (Python)" url: "/docs/proxy/lens/integrations/vercel-ai-sdk-py" canonical_url: "https://docs.litellm.ai/docs/proxy/lens/integrations/vercel-ai-sdk-py" type: "docs" last_updated: "2026-10-15" summary: "Run Vercel AI SDK (Python) examples and send their agent traces to LiteLLM Lens." related: - "/docs/proxy/lens/integrations/vercel-ai-sdk-js" - "/docs/proxy/lens/integrations/mastra" --- # Vercel AI SDK (Python) > Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt # Vercel AI SDK (Python) For optional help from your coding agent, use [Set it up for me](https://github.com/BerriAI/lens/blob/main/docs/setup-with-agent.md#connect-an-agent-to-lens-already-running). It preserves your model connection and verifies a real trace after setup Send Vercel AI SDK (Python) traces to [LiteLLM Lens](/docs/proxy/lens) using the runnable examples in this repository. ## Prerequisites You need [Lens installed alongside LiteLLM](/docs/proxy/lens/deployment#configure-an-existing-proxy), a key with model access, and a configured model alias. The swarm example needs a model that supports tool calls. In **Lens > Traces > Set up tracing**, click **Generate tracing key** and copy the **Traces endpoint** under **Connection details**. Ask your administrator for these if you cannot create a tracing key. Install [uv](https://docs.astral.sh/uv/getting-started/installation/). It uses the checked-in Python version and resolves each example’s dependencies from its uv workspace. ## Configuration For a fresh checkout: ```bash git clone https://github.com/BerriAI/litellm-lens-example.git cd litellm-lens-example/vercel-ai-sdk-py cp .env.example .env ``` If you already cloned the repository, run the remaining commands from `vercel-ai-sdk-py/`. Copy [.env.example](https://github.com/BerriAI/litellm-lens-example/blob/a2294277609202247b71c08d7b491f5212809988/vercel-ai-sdk-py/.env.example) to `.env` if it does not exist, then set: | Variable | Value | | --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `LITELLM_GATEWAY_URL` | Your gateway’s base URL without a trailing slash or `/v1`, for example `http://localhost:4002` | | `LITELLM_API_KEY` | Your LiteLLM model key | | `LENS_URL` | Copy **Traces endpoint** from Lens tracing setup and remove the final `/v1/traces`. Keep `/lens-ingest` if present. For example, `http://localhost:4318` or `https://gateway.example/lens-ingest` | | `LENS_TRACING_KEY` | The dedicated tracing key from Lens tracing setup | | `LITELLM_MODEL` | A model alias configured on your gateway | The checked-in values target a local development gateway. Replace them for your deployment. Keep the exporter settings from `.env.example`; the examples configure their trace exporters in code. They send traces to `LENS_URL/v1/traces` with the tracing key as a bearer token. Leave `MOCK_LITELLM_GATEWAY_URL` unset unless you intend to send an additional trace copy to the local [recorder](https://github.com/BerriAI/litellm-lens-example/blob/a2294277609202247b71c08d7b491f5212809988/recorder/AGENTS.md). ## Run an example ### Simple agent A `research_agent` answers one question using the Python ai package. ```bash uv run --env-file .env --package lens-vercel-ai-sdk-py-simple simple/main.py ``` See [simple/main.py](https://github.com/BerriAI/litellm-lens-example/blob/a2294277609202247b71c08d7b491f5212809988/vercel-ai-sdk-py/simple/main.py) for the implementation. ### Agent swarm A coordinator delegates through tools that run `search_agent` and `writer_agent`. ```bash uv run --env-file .env --package lens-vercel-ai-sdk-py-swarm swarm/main.py ``` See [swarm/main.py](https://github.com/BerriAI/litellm-lens-example/blob/a2294277609202247b71c08d7b491f5212809988/vercel-ai-sdk-py/swarm/main.py) for the implementation. ## Verify the trace After the example prints its answer, open **Lens > Traces** on your gateway and select the new run. Look for the run associated with `research_agent`. Inspect the input, output, and model spans. For the swarm, inspect the specialist activity described above; its exact span layout depends on the framework. ## How tracing works The Python ai package’s experimental telemetry adapter exports agent, tool, and model spans. A local adapter keeps model spans in the active context so the shared gateway transport can nest request-attempt spans beneath them. See the [shared gateway transport](https://github.com/BerriAI/litellm-lens-example/blob/a2294277609202247b71c08d7b491f5212809988/shared/README.md) for request-attempt and spend-correlation details. ## Troubleshooting If model calls fail, check the gateway URL, key, and model alias. If an answer appears but the trace is missing, check the terminal for exporter errors and confirm the Lens ingestion service is reachable with your tracing key. A model call succeeding does not confirm that its trace export succeeded. This example uses the Python ai package and its experimental telemetry API. Its dependencies and setup differ from the TypeScript example. ## Related pages - [Vercel AI SDK (TypeScript)](https://docs.litellm.ai/docs/proxy/lens/integrations/vercel-ai-sdk-js.md) - [Mastra](https://docs.litellm.ai/docs/proxy/lens/integrations/mastra.md)