Files

Hoong Tee, Yeoh a719b61813 [rerank]: Refine documentation for rerank comps (#758 )

* [rerank]: Refine documentation for rerank comps

Restructure and refine README documentation for rerank components.

Signed-off-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* rerank-doc: Break up README lines for viewing experience

Signed-off-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com>

---------

Signed-off-by: Yeoh, Hoong Tee <hoong.tee.yeoh@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>

2024-10-14 15:35:33 +08:00

3.3 KiB

Raw Blame History

Reranking Microservice via TEI

Text Embeddings Inference (TEI) is a comprehensive toolkit designed for efficient deployment and serving of open source text embeddings models. It enable us to host our own reranker endpoint seamlessly.

This README provides set-up instructions and comprehensive details regarding the reranking microservice via TEI.

🚀1. Start Microservice with Python (Option 1)

To start the Reranking microservice, you must first install the required python packages.

1.1 Install Requirements

pip install -r requirements.txt

1.2 Start TEI Service

export HF_TOKEN=${your_hf_api_token}
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export volume=$PWD/data

docker run -d -p 6060:80 -v $volume:/data -e http_proxy=$http_proxy -e https_proxy=$https_proxy --pull always ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 --model-id $RERANK_MODEL_ID --hf-api-token $HF_TOKEN

1.3 Verify the TEI Service

curl 127.0.0.1:6060/rerank \
    -X POST \
    -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \
    -H 'Content-Type: application/json'

1.4 Start Reranking Service with Python Script

export TEI_RERANKING_ENDPOINT="http://${your_ip}:6060"

python reranking_tei_xeon.py

🚀2. Start Microservice with Docker (Option 2)

If you start an Reranking microservice with docker, the docker_compose_reranking.yaml file will automatically start a TEI service with docker.

2.1 Setup Environment Variables

export HF_TOKEN=${your_hf_api_token}
export TEI_RERANKING_ENDPOINT="http://${your_ip}:8808"

2.2 Build Docker Image

cd ../../../
docker build -t opea/reranking-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/reranks/tei/Dockerfile .

To start a docker container, you have two options:

A. Run Docker with CLI
B. Run Docker with Docker Compose

You can choose one as needed.

2.3 Run Docker with CLI (Option A)

docker run -d --name="reranking-tei-server" -p 8000:8000 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e TEI_RERANKING_ENDPOINT=$TEI_RERANKING_ENDPOINT -e HF_TOKEN=$HF_TOKEN opea/reranking-tei:latest

2.4 Run Docker with Docker Compose (Option B)

docker compose -f docker_compose_reranking.yaml up -d

✅3. Invoke Reranking Microservice

The Reranking microservice exposes following API endpoints:

Check Service Status

curl http://localhost:8000/v1/health_check \
  -X GET \
  -H 'Content-Type: application/json'

Execute reranking process by providing query and documents

curl http://localhost:8000/v1/reranking \
  -X POST \
  -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}' \
  -H 'Content-Type: application/json'

You can add the parameter top_n to specify the return number of the reranker model, default value is 1.

curl http://localhost:8000/v1/reranking \
  -X POST \
  -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}], "top_n":2}' \
  -H 'Content-Type: application/json'

3.3 KiB Raw Blame History