add VDMS retriever microservice for v0.9 Milestone

comps/__init__.py

@@ -12,6 +12,7 @@
     GeneratedDoc,
     LLMParamsDoc,
     SearchedDoc,
+    SearchedMultimodalDoc,
     RerankedDoc,
     TextDoc,
     RAGASParams,

comps/cores/proto/docarray.py

@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-from typing import Dict, List, Optional, Union
+from typing import Dict, List, Optional, Tuple, Union
 
 import numpy as np
 from docarray import BaseDoc, DocList
@@ -20,6 +20,14 @@ class TextDoc(BaseDoc, TopologyInfo):
     text: str
 
 
+class ImageDoc(BaseDoc):
+    image_path: str
+
+
+class TextImageDoc(BaseDoc):
+    doc: Tuple[Union[TextDoc, ImageDoc]]
+
+
 class Base64ByteStrDoc(BaseDoc):
     byte_str: str
 
@@ -41,6 +49,7 @@ class EmbedDoc(BaseDoc):
     fetch_k: int = 20
     lambda_mult: float = 0.5
     score_threshold: float = 0.2
+    constraints: dict = None
 
 
 class Audio2TextDoc(AudioDoc):
@@ -67,6 +76,16 @@ class Config:
         json_encoders = {np.ndarray: lambda x: x.tolist()}
 
 
+class SearchedMultimodalDoc(BaseDoc):
+    retrieved_docs: List[TextImageDoc]
+    initial_query: str
+    top_n: int = 1
+    metadata: Optional[List[Dict]] = None
+
+    class Config:
+        json_encoders = {np.ndarray: lambda x: x.tolist()}
+
+
 class GeneratedDoc(BaseDoc):
     text: str
     prompt: str

comps/retrievers/langchain/README.md

@@ -6,14 +6,18 @@ The service primarily utilizes similarity measures in vector space to rapidly re
 
 Overall, this microservice provides robust backend support for applications requiring efficient similarity searches, playing a vital role in scenarios such as recommendation systems, information retrieval, or any other context where precise measurement of document similarity is crucial.
 
-## Retriever Microservice with Redis
+# Retriever Microservice with Redis
 
 For details, please refer to this [readme](redis/README.md)
 
-## Retriever Microservice with Milvus
+# Retriever Microservice with Milvus
 
 For details, please refer to this [readme](milvus/README.md)
 
-## Retriever Microservice with PGVector
+# Retriever Microservice with PGVector
 
 For details, please refer to this [readme](pgvector/README.md)
+
+# Retriever Microservice with VDMS
+
+For details, please refer to this [readme](vdms/README.md)

comps/retrievers/langchain/vdms/README.md

@@ -0,0 +1,152 @@
+# Retriever Microservice
+
+This retriever microservice is a highly efficient search service designed for handling and retrieving embedding vectors. It operates by receiving an embedding vector as input and conducting a similarity search against vectors stored in a VectorDB database. Users must specify the VectorDB's host, port, and the index/collection name, and the service searches within that index to find documents with the highest similarity to the input vector.
+
+The service primarily utilizes similarity measures in vector space to rapidly retrieve contentually similar documents. The vector-based retrieval approach is particularly suited for handling large datasets, offering fast and accurate search results that significantly enhance the efficiency and quality of information retrieval.
+
+Overall, this microservice provides robust backend support for applications requiring efficient similarity searches, playing a vital role in scenarios such as recommendation systems, information retrieval, or any other context where precise measurement of document similarity is crucial.
+
+# 🚀1. Start Microservice with Python (Option 1)
+
+To start the retriever microservice, you must first install the required python packages.
+
+## 1.1 Install Requirements
+
+```bash
+pip install -r requirements.txt
+```
+
+## 1.2 Start TEI Service
+
+```bash
+export LANGCHAIN_TRACING_V2=true
+export LANGCHAIN_API_KEY=${your_langchain_api_key}
+export LANGCHAIN_PROJECT="opea/retriever"
+model=BAAI/bge-base-en-v1.5
+revision=refs/pr/4
+volume=$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-1.2 --model-id $model --revision $revision
+```
+
+## 1.3 Verify the TEI Service
+
+```bash
+curl 127.0.0.1:6060/rerank \
+    -X POST \
+    -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \
+    -H 'Content-Type: application/json'
+```
+
+## 1.4 Setup VectorDB Service
+
+You need to setup your own VectorDB service (VDMS in this example), and ingest your knowledge documents into the vector database.
+
+As for VDMS, you could start a docker container using the following commands.
+Remember to ingest data into it manually.
+
+```bash
+docker run -d --name="vdms-vector-db" -p 55555:55555 intellabs/vdms:latest
+```
+
+## 1.5 Start Retriever Service
+
+```bash
+export TEI_EMBEDDING_ENDPOINT="http://${your_ip}:6060"
+python langchain/retriever_vdms.py
+```
+
+# 🚀2. Start Microservice with Docker (Option 2)
+
+## 2.1 Setup Environment Variables
+
+```bash
+export RETRIEVE_MODEL_ID="BAAI/bge-base-en-v1.5"
+export COLLECTION_NAME=${your_index_name}
+export TEI_EMBEDDING_ENDPOINT="http://${your_ip}:6060"
+export LANGCHAIN_TRACING_V2=true
+export LANGCHAIN_API_KEY=${your_langchain_api_key}
+export LANGCHAIN_PROJECT="opea/retrievers"
+```
+
+## 2.2 Build Docker Image
+
+```bash
+cd ../../
+docker build -t opea/retriever-vdms:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/retrievers/langchain/vdms/docker/Dockerfile .
+```
+
+To start a docker container, you have two options:
+
+- A. Run Docker with CLI
+- B. Run Docker with Docker Compose
+
+You can choose one as needed.
+
+## 2.3 Run Docker with CLI (Option A)
+
+```bash
+docker run -d --name="retriever-vdms-server" -p 7000:7000 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e INDEX_NAME=$COLLECTION_NAME -e TEI_EMBEDDING_ENDPOINT=$TEI_EMBEDDING_ENDPOINT opea/retriever-vdms:latest
+```
+
+## 2.4 Run Docker with Docker Compose (Option B)
+
+```bash
+cd langchain/vdms/docker
+docker compose -f docker_compose_retriever.yaml up -d
+```
+
+# 🚀3. Consume Retriever Service
+
+## 3.1 Check Service Status
+
+```bash
+curl http://localhost:7000/v1/health_check \
+  -X GET \
+  -H 'Content-Type: application/json'
+```
+
+## 3.2 Consume Embedding Service
+
+To consume the Retriever Microservice, you can generate a mock embedding vector of length 768 with Python.
+
+```bash
+your_embedding=$(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.
+
+```bash
+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'
+```
+
+```bash
+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'
+```
+
+```bash
+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'
+```
+
+```bash
+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'
+```

comps/retrievers/langchain/vdms/__init__.py

@@ -0,0 +1,2 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0

comps/retrievers/langchain/vdms/docker/Dockerfile

@@ -0,0 +1,49 @@
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+FROM langchain/langchain:latest
+
+ARG ARCH="cpu"
+
+RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
+    libgl1-mesa-glx \
+    libjemalloc-dev \
+    iputils-ping \
+    vim
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user/
+
+COPY comps /home/user/comps
+
+# RUN chmod +x /home/user/comps/retrievers/langchain/vdms/run.sh
+
+USER user
+RUN pip install --no-cache-dir --upgrade pip && \
+    if [ ${ARCH} = "cpu" ]; then pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu; fi && \
+    pip install --no-cache-dir -r /home/user/comps/retrievers/langchain/vdms/requirements.txt
+
+RUN pip install -U langchain
+RUN pip install -U langchain-community
+
+RUN pip install --upgrade huggingface-hub
+
+ENV PYTHONPATH=$PYTHONPATH:/home/user
+
+ENV HUGGINGFACEHUB_API_TOKEN=dummy
+
+ENV USECLIP 0
+
+ENV no_proxy=localhost,127.0.0.1
+
+ENV http_proxy=""
+ENV https_proxy=""
+
+WORKDIR /home/user/comps/retrievers/langchain/vdms
+
+#ENTRYPOINT ["/home/user/comps/retrievers/langchain/vdms/run.sh"]
+#ENTRYPOINT ["/bin/bash"]
+
+ENTRYPOINT ["python", "retriever_vdms.py"]

comps/retrievers/langchain/vdms/docker/docker_compose_retriever.yaml

@@ -0,0 +1,32 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+version: "3.8"
+
+services:
+  tei_xeon_service:
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
+    container_name: tei-xeon-server
+    ports:
+      - "6060:80"
+    volumes:
+      - "./data:/data"
+    shm_size: 1g
+    command: --model-id ${RETRIEVE_MODEL_ID}
+  retriever:
+    image: opea/retriever-vdms:latest
+    container_name: retriever-vdms-server
+    ports:
+      - "7000:7000"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      COLLECTION_NAME: ${COLLECTION_NAME}
+      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
+    restart: unless-stopped
+
+networks:
+  default:
+    driver: bridge