pip install -r requirements.txt
Please refer to this readme.
export no_proxy=${your_no_proxy}
export http_proxy=${your_http_proxy}
export https_proxy=${your_http_proxy}
export MILVUS_HOST=${your_milvus_host_ip}
export MILVUS_PORT=19530
export COLLECTION_NAME=${your_collection_name}
export MOSEC_EMBEDDING_ENDPOINT=${your_emdding_endpoint}
export MOSEC_EMBEDDING_ENDPOINT="http://${your_ip}:6060"
python retriever_redis.py
cd ../../
docker build -t opea/retriever-milvus:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/retrievers/milvus/langchain/Dockerfile .
docker run -d --name="retriever-milvus-server" -p 7000:7000 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e MOSEC_EMBEDDING_ENDPOINT=${your_emdding_endpoint} -e MILVUS_HOST=${your_milvus_host_ip} opea/retriever-milvus:latest
curl http://${your_ip}:7000/v1/health_check \
-X GET \
-H 'Content-Type: application/json'
To consume the Retriever Microservice, you can generate a mock embedding vector of length 768 with Python.
export your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
curl http://${your_ip}:7000/v1/retrieval \
-X POST \
-d "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${your_embedding}}" \
-H 'Content-Type: application/json'
You can set the parameters for the retriever.
export your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
curl http://localhost:7000/v1/retrieval \
-X POST \
-d "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${your_embedding},\"search_type\":\"similarity\", \"k\":4}" \
-H 'Content-Type: application/json'
export your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
curl http://localhost:7000/v1/retrieval \
-X POST \
-d "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${your_embedding},\"search_type\":\"similarity_distance_threshold\", \"k\":4, \"distance_threshold\":1.0}" \
-H 'Content-Type: application/json'
export your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
curl http://localhost:7000/v1/retrieval \
-X POST \
-d "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${your_embedding},\"search_type\":\"similarity_score_threshold\", \"k\":4, \"score_threshold\":0.2}" \
-H 'Content-Type: application/json'
export your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
curl http://localhost:7000/v1/retrieval \
-X POST \
-d "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${your_embedding},\"search_type\":\"mmr\", \"k\":4, \"fetch_k\":20, \"lambda_mult\":0.5}" \
-H 'Content-Type: application/json'