vllm-haystack 1.0.0

Haystack integration for vllm

vllm-haystack

• Changelog

---

Contributing

Refer to the general Contribution Guidelines.

To run integration tests locally, you need two vLLM servers running in parallel: one for the chat generator on port 8000 and one for the embedders on port 8001. Refer to the workflow file for more details.

For example, on macOs, you can install vLLM-metal and start the chat generator server with:

# chat generator server (port 8000)
source ~/.venv-vllm-metal/bin/activate && vllm serve Qwen/Qwen3-0.6B --reasoning-parser qwen3 --max-model-len 1024 --enforce-eager --enable-auto-tool-choice --tool-call-parser hermes

vLLM-metal does not support embedding models. On macOS, you can run the embedding server via CPU Docker image:

# embedders server (port 8001)
docker run --rm -p 8001:8000 -e VLLM_CPU_OMP_THREADS_BIND=0-3 vllm/vllm-openai-cpu:latest \
    --model sentence-transformers/all-MiniLM-L6-v2 --enforce-eager