Merge branch 'main' into refine_component_interface

.github/workflows/docker/compose/agent-compose.yaml

@@ -3,7 +3,7 @@
 
 # this file should be run in the root of the repo
 services:
-  agent-langchain:
+  agent:
     build:
-      dockerfile: comps/agent/langchain/Dockerfile
-    image: ${REGISTRY:-opea}/agent-langchain:${TAG:-latest}
+      dockerfile: comps/agent/src/Dockerfile
+    image: ${REGISTRY:-opea}/agent:${TAG:-latest}

.github/workflows/docker/compose/embeddings-compose.yaml

@@ -3,10 +3,10 @@
 
 # this file should be run in the root of the repo
 services:
-  embedding-tei:
+  embedding:
     build:
       dockerfile: comps/embeddings/src/Dockerfile
-    image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
+    image: ${REGISTRY:-opea}/embedding:${TAG:-latest}
   embedding-multimodal-clip:
     build:
       dockerfile: comps/embeddings/src/integrations/dependency/clip/Dockerfile
@@ -15,15 +15,7 @@ services:
     build:
       dockerfile: comps/embeddings/src/integrations/dependency/bridgetower/Dockerfile
     image: ${REGISTRY:-opea}/embedding-multimodal-bridgetower:${TAG:-latest}
-  embedding-multimodal:
-    build:
-      dockerfile: comps/embeddings/src/Dockerfile
-    image: ${REGISTRY:-opea}/embedding-multimodal:${TAG:-latest}
   embedding-multimodal-bridgetower-gaudi:
     build:
       dockerfile: comps/embeddings/src/integrations/dependency/bridgetower/Dockerfile.intel_hpu
     image: ${REGISTRY:-opea}/embedding-multimodal-bridgetower-gaudi:${TAG:-latest}
-  embedding-predictionguard:
-    build:
-      dockerfile: comps/embeddings/src/Dockerfile
-    image: ${REGISTRY:-opea}/embedding-predictionguard:${TAG:-latest}

.github/workflows/docker/compose/llms-compose.yaml

@@ -3,10 +3,10 @@
 
 # this file should be run in the root of the repo
 services:
-  llm-tgi:
+  llm-textgen:
     build:
       dockerfile: comps/llms/src/text-generation/Dockerfile
-    image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
+    image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}
   llm-ollama:
     build:
       dockerfile: comps/llms/text-generation/ollama/langchain/Dockerfile
@@ -19,10 +19,6 @@ services:
     build:
       dockerfile: comps/llms/faq-generation/tgi/langchain/Dockerfile
     image: ${REGISTRY:-opea}/llm-faqgen-tgi:${TAG:-latest}
-  llm-vllm:
-    build:
-      dockerfile: comps/llms/src/text-generation/Dockerfile
-    image: ${REGISTRY:-opea}/llm-vllm:${TAG:-latest}
   llm-native:
     build:
       dockerfile: comps/llms/text-generation/native/langchain/Dockerfile

.github/workflows/docker/compose/reranks-compose.yaml

@@ -3,15 +3,7 @@
 
 # this file should be run in the root of the repo
 services:
-  reranking-tei:
+  reranking:
     build:
       dockerfile: comps/reranks/src/Dockerfile
-    image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
-  reranking-videoqna:
-    build:
-      dockerfile: comps/reranks/src/Dockerfile # TODO. need to update
-    image: ${REGISTRY:-opea}/reranking-videoqna:${TAG:-latest}
-  reranking-fastrag:
-    build:
-      dockerfile: comps/reranks/src/Dockerfile # TODO. need to update
-    image: ${REGISTRY:-opea}/reranking-fastrag:${TAG:-latest}
+    image: ${REGISTRY:-opea}/reranking:${TAG:-latest}

.github/workflows/scripts/check_duplicated_image.py

@@ -9,6 +9,8 @@
 import yaml
 
 images = {}
+dockerfiles = {}
+errors = []
 
 
 def check_docker_compose_build_definition(file_path):
@@ -30,18 +32,26 @@ def check_docker_compose_build_definition(file_path):
                 if not os.path.exists(dockerfile):
                     # dockerfile not exists in the current repo context, assume it's in 3rd party context
                     dockerfile = os.path.normpath(os.path.join(context, build.get("dockerfile", "")))
-                item = {"file_path": file_path, "service": service, "dockerfile": dockerfile}
+                item = {"file_path": file_path, "service": service, "dockerfile": dockerfile, "image": image}
                 if image in images and dockerfile != images[image]["dockerfile"]:
-                    print("ERROR: !!! Found Conflicts !!!")
-                    print(f"Image: {image}, Dockerfile: {dockerfile}, defined in Service: {service}, File: {file_path}")
-                    print(
+                    errors.append(
+                        f"ERROR: !!! Found Conflicts !!!\n"
+                        f"Image: {image}, Dockerfile: {dockerfile}, defined in Service: {service}, File: {file_path}\n"
                         f"Image: {image}, Dockerfile: {images[image]['dockerfile']}, defined in Service: {images[image]['service']}, File: {images[image]['file_path']}"
                     )
-                    sys.exit(1)
                 else:
                     # print(f"Add Image: {image} Dockerfile: {dockerfile}")
                     images[image] = item
 
+                if dockerfile in dockerfiles and image != dockerfiles[dockerfile]["image"]:
+                    errors.append(
+                        f"WARNING: Different images using the same Dockerfile\n"
+                        f"Dockerfile: {dockerfile}, Image: {image}, defined in Service: {service}, File: {file_path}\n"
+                        f"Dockerfile: {dockerfile}, Image: {dockerfiles[dockerfile]['image']}, defined in Service: {dockerfiles[dockerfile]['service']}, File: {dockerfiles[dockerfile]['file_path']}"
+                    )
+                else:
+                    dockerfiles[dockerfile] = item
+
 
 def parse_arg():
     parser = argparse.ArgumentParser(
@@ -55,6 +65,10 @@ def main():
     args = parse_arg()
     for file_path in args.files:
         check_docker_compose_build_definition(file_path)
+    if errors:
+        for error in errors:
+            print(error)
+        sys.exit(1)
     print("SUCCESS: No Conlicts Found.")
     return 0
 

comps/agent/langchain/Dockerfile → comps/agent/src/Dockerfile

@@ -21,19 +21,19 @@ COPY comps /home/user/comps
 
 RUN pip install --no-cache-dir --upgrade pip setuptools && \
     if [ ${ARCH} = "cpu" ]; then \
-        pip install --no-cache-dir --extra-index-url https://download.pytorch.org/whl/cpu -r /home/user/comps/agent/langchain/requirements.txt; \
+        pip install --no-cache-dir --extra-index-url https://download.pytorch.org/whl/cpu -r /home/user/comps/agent/src/requirements.txt; \
     else \
-        pip install --no-cache-dir -r /home/user/comps/agent/langchain/requirements.txt; \
+        pip install --no-cache-dir -r /home/user/comps/agent/src/requirements.txt; \
     fi
 
 ENV PYTHONPATH=$PYTHONPATH:/home/user
 
 USER root
 
-RUN mkdir -p /home/user/comps/agent/langchain/status && chown -R user /home/user/comps/agent/langchain/status
+RUN mkdir -p /home/user/comps/agent/src/status && chown -R user /home/user/comps/agent/src/status
 
 USER user
 
-WORKDIR /home/user/comps/agent/langchain/
+WORKDIR /home/user/comps/agent/src/
 
 ENTRYPOINT ["python", "agent.py"]

comps/agent/langchain/README.md → comps/agent/src/README.md

@@ -11,7 +11,7 @@ We currently support the following types of agents. Please refer to the example
 1. ReAct: use `react_langchain` or `react_langgraph` or `react_llama` as strategy. First introduced in this seminal [paper](https://arxiv.org/abs/2210.03629). The ReAct agent engages in "reason-act-observe" cycles to solve problems. Please refer to this [doc](https://python.langchain.com/v0.2/docs/how_to/migrate_agent/) to understand the differences between the langchain and langgraph versions of react agents. See table below to understand the validated LLMs for each react strategy.
 2. RAG agent: use `rag_agent` or `rag_agent_llama` strategy. This agent is specifically designed for improving RAG performance. It has the capability to rephrase query, check relevancy of retrieved context, and iterate if context is not relevant. See table below to understand the validated LLMs for each rag agent strategy.
 3. Plan and execute: `plan_execute` strategy. This type of agent first makes a step-by-step plan given a user request, and then execute the plan sequentially (or in parallel, to be implemented in future). If the execution results can solve the problem, then the agent will output an answer; otherwise, it will replan and execute again.
-4. SQL agent: use `sql_agent_llama` or `sql_agent` strategy. This agent is specifically designed and optimized for answering questions aabout data in SQL databases. Users need to specify `db_name` and `db_path` for the agent to access the SQL database. For more technical details read descriptions [here](src/strategy/sqlagent/README.md).
+4. SQL agent: use `sql_agent_llama` or `sql_agent` strategy. This agent is specifically designed and optimized for answering questions aabout data in SQL databases. Users need to specify `db_name` and `db_path` for the agent to access the SQL database. For more technical details read descriptions [here](integrations/strategy/sqlagent/README.md).
 
 **Note**:
 
@@ -60,7 +60,7 @@ Examples of how to register tools can be found in [Section 4](#-4-provide-your-o
 
 ```bash
 cd GenAIComps/ # back to GenAIComps/ folder
-docker build -t opea/agent-langchain:latest -f comps/agent/langchain/Dockerfile . --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy
+docker build -t opea/agent:latest -f comps/agent/src/Dockerfile . --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy
 ```
 
 #### 2.2.1 Start Agent microservices with TGI
@@ -78,7 +78,7 @@ docker run -d --runtime=habana --name "comps-tgi-gaudi-service" -p 8080:80 -v ./
 docker logs comps-tgi-gaudi-service
 
 # Agent: react_llama strategy
-docker run -d --runtime=runc --name="comps-langchain-agent-endpoint" -v $WORKPATH/comps/agent/langchain/tools:/home/user/comps/agent/langchain/tools -p 9090:9090 --ipc=host -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e model=${model} -e ip_address=${ip_address} -e strategy=react_llama -e llm_endpoint_url=http://${ip_address}:8080 -e llm_engine=tgi -e recursion_limit=15 -e require_human_feedback=false -e tools=/home/user/comps/agent/langchain/tools/custom_tools.yaml opea/agent-langchain:latest
+docker run -d --runtime=runc --name="comps-langchain-agent-endpoint" -v $WORKPATH/comps/agent/langchain/tools:/home/user/comps/agent/langchain/tools -p 9090:9090 --ipc=host -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e model=${model} -e ip_address=${ip_address} -e strategy=react_llama -e llm_endpoint_url=http://${ip_address}:8080 -e llm_engine=tgi -e recursion_limit=15 -e require_human_feedback=false -e tools=/home/user/comps/agent/langchain/tools/custom_tools.yaml opea/agent:latest
 
 # check status
 docker logs comps-langchain-agent-endpoint
@@ -105,7 +105,7 @@ docker run -d --runtime=habana --rm --name "comps-vllm-gaudi-service" -p 8080:80
 docker logs comps-vllm-gaudi-service
 
 # Agent
-docker run -d --runtime=runc --name="comps-langchain-agent-endpoint" -v $WORKPATH/comps/agent/langchain/tools:/home/user/comps/agent/langchain/tools -p 9090:9090 --ipc=host -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e model=${model} -e ip_address=${ip_address} -e strategy=react_llama -e llm_endpoint_url=http://${ip_address}:8080 -e llm_engine=vllm -e recursion_limit=15 -e require_human_feedback=false -e tools=/home/user/comps/agent/langchain/tools/custom_tools.yaml opea/agent-langchain:latest
+docker run -d --runtime=runc --name="comps-langchain-agent-endpoint" -v $WORKPATH/comps/agent/langchain/tools:/home/user/comps/agent/langchain/tools -p 9090:9090 --ipc=host -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e model=${model} -e ip_address=${ip_address} -e strategy=react_llama -e llm_endpoint_url=http://${ip_address}:8080 -e llm_engine=vllm -e recursion_limit=15 -e require_human_feedback=false -e tools=/home/user/comps/agent/langchain/tools/custom_tools.yaml opea/agent:latest
 
 # check status
 docker logs comps-langchain-agent-endpoint
@@ -114,7 +114,7 @@ docker logs comps-langchain-agent-endpoint
 > debug mode
 >
 > ```bash
-> docker run --rm --runtime=runc --name="comps-langchain-agent-endpoint" -v ./comps/agent/langchain/:/home/user/comps/agent/langchain/ -p 9090:9090 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e model=${model} -e ip_address=${ip_address} -e strategy=react_llama -e llm_endpoint_url=http://${ip_address}:8080 -e llm_engine=vllm -e recursion_limit=15 -e require_human_feedback=false -e tools=/home/user/comps/agent/langchain/tools/custom_tools.yaml opea/agent-langchain:latest
+> docker run --rm --runtime=runc --name="comps-langchain-agent-endpoint" -v ./comps/agent/langchain/:/home/user/comps/agent/langchain/ -p 9090:9090 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e model=${model} -e ip_address=${ip_address} -e strategy=react_llama -e llm_endpoint_url=http://${ip_address}:8080 -e llm_engine=vllm -e recursion_limit=15 -e require_human_feedback=false -e tools=/home/user/comps/agent/langchain/tools/custom_tools.yaml opea/agent:latest
 > ```
 
 ## 🚀 3. Validate Microservice
@@ -189,7 +189,7 @@ def opea_rag_query(query):
 
 ```bash
 # Agent
-docker run -d --runtime=runc --name="comps-langchain-agent-endpoint" -v my_tools:/home/user/comps/agent/langchain/tools -p 9090:9090 --ipc=host -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e model=${model} -e ip_address=${ip_address} -e strategy=react_llama -e llm_endpoint_url=http://${ip_address}:8080 -e llm_engine=tgi -e recursive_limit=15 -e require_human_feedback=false -e tools=/home/user/comps/agent/langchain/tools/custom_tools.yaml opea/agent-langchain:latest
+docker run -d --runtime=runc --name="comps-langchain-agent-endpoint" -v my_tools:/home/user/comps/agent/langchain/tools -p 9090:9090 --ipc=host -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e model=${model} -e ip_address=${ip_address} -e strategy=react_llama -e llm_endpoint_url=http://${ip_address}:8080 -e llm_engine=tgi -e recursive_limit=15 -e require_human_feedback=false -e tools=/home/user/comps/agent/langchain/tools/custom_tools.yaml opea/agent:latest
 ```
 
 - validate with my_tools
@@ -205,5 +205,5 @@ data: [DONE]
 
 ## 5. Customize agent strategy
 
-For advanced developers who want to implement their own agent strategies, you can add a separate folder in `src\strategy`, implement your agent by inherit the `BaseAgent` class, and add your strategy into the `src\agent.py`. The architecture of this agent microservice is shown in the diagram below as a reference.
+For advanced developers who want to implement their own agent strategies, you can add a separate folder in `integrations\strategy`, implement your agent by inherit the `BaseAgent` class, and add your strategy into the `integrations\agent.py`. The architecture of this agent microservice is shown in the diagram below as a reference.
 ![Architecture Overview](agent_arch.jpg)

comps/agent/langchain/agent.py → comps/agent/src/agent.py

@@ -14,10 +14,10 @@
 sys.path.append(comps_path)
 
 from comps import CustomLogger, GeneratedDoc, LLMParamsDoc, ServiceType, opea_microservices, register_microservice
-from comps.agent.langchain.src.agent import instantiate_agent
-from comps.agent.langchain.src.global_var import assistants_global_kv, threads_global_kv
-from comps.agent.langchain.src.thread import instantiate_thread_memory, thread_completion_callback
-from comps.agent.langchain.src.utils import get_args
+from comps.agent.src.integrations.agent import instantiate_agent
+from comps.agent.src.integrations.global_var import assistants_global_kv, threads_global_kv
+from comps.agent.src.integrations.thread import instantiate_thread_memory, thread_completion_callback
+from comps.agent.src.integrations.utils import get_args
 from comps.cores.proto.api_protocol import (
     AssistantsObject,
     ChatCompletionRequest,

comps/agent/langchain/test.py → comps/agent/src/test.py

@@ -8,11 +8,11 @@
 
 import pandas as pd
 import requests
-from src.utils import get_args
+from integrations.utils import get_args
 
 
 def test_agent_local(args):
-    from src.agent import instantiate_agent
+    from integrations.agent import instantiate_agent
 
     if args.q == 0:
         df = pd.DataFrame({"query": ["What is the Intel OPEA Project?"]})
@@ -148,7 +148,7 @@ def process_request(api, query, is_stream=False):
 
 
 def test_ut(args):
-    from src.tools import get_tools_descriptions
+    from integrations.tools import get_tools_descriptions
 
     tools = get_tools_descriptions("tools/custom_tools.py")
     for tool in tools:

comps/agent/langchain/test_assistant_api.py → comps/agent/src/test_assistant_api.py

@@ -5,7 +5,7 @@
 import json
 
 import requests
-from src.utils import get_args
+from integrations.utils import get_args
 
 
 def test_assistants_http(args):

comps/embeddings/deployment/docker_compose/compose_multimodal_bridgetower.yaml

@@ -20,7 +20,7 @@ services:
       timeout: 6s
       retries: 18
       start_period: 30s
-  embedding-multimodal:
+  embedding:
     image: opea/embedding:latest
     container_name: embedding-multimodal-bridgetower-server
     ports:

comps/embeddings/deployment/docker_compose/compose_multimodal_bridgetower_intel_hpu.yaml

@@ -24,7 +24,7 @@ services:
       timeout: 6s
       retries: 18
       start_period: 30s
-  embedding-multimodal:
+  embedding:
     image: opea/embedding:latest
     container_name: embedding-multimodal-bridgetower-server
     ports:

comps/embeddings/deployment/docker_compose/compose_predictionguard.yaml

@@ -4,7 +4,7 @@
 services:
   embedding:
     image: opea/embedding:latest
-    container_name: embedding-predictionguard
+    container_name: embedding
     ports:
       - "6000:6000"
     ipc: host

comps/embeddings/deployment/docker_compose/compose_tei.yaml

@@ -24,7 +24,7 @@ services:
       retries: 18
   embedding:
     image: opea/embedding:latest
-    container_name: embedding-tei-server
+    container_name: embedding-server
     ports:
       - "6000:6000"
     ipc: host

comps/llms/deployment/docker_compose/text-generation_vllm_langchain.yaml

@@ -25,7 +25,7 @@ services:
     ipc: host
     command: --model $LLM_MODEL --tensor-parallel-size 1 --host 0.0.0.0 --port 80
   llm:
-    image: opea/llm-vllm:latest
+    image: opea/llm-textgen:latest
     container_name: llm-vllm-gaudi-server
     depends_on:
       - vllm-service

comps/llms/src/text-generation/README.md

@@ -41,7 +41,7 @@ export LLM_MODEL_ID=${your_hf_llm_model}
 
 ```bash
 cd ../../../../
-docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile .
+docker build -t opea/llm-textgen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile .
 ```
 
 To start a docker container, you have two options:
@@ -54,7 +54,7 @@ You can choose one as needed.
 ### 2.3 Run Docker with CLI (Option A)
 
 ```bash
-docker run -d --name="llm-tgi-server" -p 9000:9000 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e TGI_LLM_ENDPOINT=$TGI_LLM_ENDPOINT -e HF_TOKEN=$HF_TOKEN opea/llm-tgi:latest
+docker run -d --name="llm-tgi-server" -p 9000:9000 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e TGI_LLM_ENDPOINT=$TGI_LLM_ENDPOINT -e HF_TOKEN=$HF_TOKEN opea/llm-textgen:latest
 ```
 
 ### 2.4 Run Docker with Docker Compose (Option B)

comps/llms/text-generation/README.md

@@ -194,7 +194,7 @@ docker run -d \
   -e https_proxy=$https_proxy \
   -e TGI_LLM_ENDPOINT=$TGI_LLM_ENDPOINT \
   -e HF_TOKEN=$HF_TOKEN \
-  opea/llm-tgi:latest
+  opea/llm-textgen:latest
 ```
 
 #### 2.3.2 vLLM
@@ -218,7 +218,7 @@ docker run \
   -e vLLM_LLM_ENDPOINT=$vLLM_LLM_ENDPOINT \
   -e HF_TOKEN=$HF_TOKEN \
   -e LLM_MODEL=$LLM_MODEL \
-  opea/llm-vllm:latest
+  opea/llm-textgen:latest
 ```
 
 ### 2.4 Run Docker with Docker Compose (Option B)

comps/llms/text-generation/vllm/langchain/docker_compose_llm.yaml

@@ -25,7 +25,7 @@ services:
     ipc: host
     command: --model $LLM_MODEL --tensor-parallel-size 1 --host 0.0.0.0 --port 80
   llm:
-    image: opea/llm-vllm:latest
+    image: opea/llm-textgen:latest
     container_name: llm-vllm-gaudi-server
     depends_on:
       - vllm-service

comps/llms/text-generation/vllm/langchain/launch_microservice.sh

@@ -11,4 +11,4 @@ docker run -d --rm \
     -e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN \
     -e LLM_MODEL=$LLM_MODEL \
     -e LOGFLAG=$LOGFLAG \
-    opea/llm-vllm:latest
+    opea/llm-textgen:latest

comps/reranks/deployment/docker_compose/rerank_tei.yaml

@@ -20,7 +20,7 @@ services:
     command: --model-id ${RERANK_MODEL_ID} --hf-api-token ${HF_TOKEN}
   reranking:
     image: opea/reranking:latest
-    container_name: reranking-tei-server
+    container_name: reranking-server
     ports:
       - "8000:8000"
     ipc: host