Agent example for v1.0 release (opea-project#684)

Signed-off-by: minmin-intel <[email protected]>
Signed-off-by: Chendi.Xue <[email protected]>

AgentQnA/docker_compose/intel/cpu/xeon/compose_openai.yaml

@@ -14,7 +14,7 @@ services:
     environment:
       ip_address: ${ip_address}
       strategy: rag_agent
-      recursion_limit: ${recursion_limit}
+      recursion_limit: ${recursion_limit_worker}
       llm_engine: openai
       OPENAI_API_KEY: ${OPENAI_API_KEY}
       model: ${model}
@@ -23,6 +23,7 @@ services:
       streaming: false
       tools: /home/user/tools/worker_agent_tools.yaml
       require_human_feedback: false
+      RETRIEVAL_TOOL_URL: ${RETRIEVAL_TOOL_URL}
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
@@ -31,6 +32,7 @@ services:
       LANGCHAIN_PROJECT: "opea-worker-agent-service"
       port: 9095
 
+
   supervisor-react-agent:
     image: opea/comps-agent-langchain:latest
     container_name: react-agent-endpoint
@@ -43,13 +45,13 @@ services:
     environment:
       ip_address: ${ip_address}
       strategy: react_langgraph
-      recursion_limit: ${recursion_limit}
+      recursion_limit: ${recursion_limit_supervisor}
       llm_engine: openai
       OPENAI_API_KEY: ${OPENAI_API_KEY}
       model: ${model}
       temperature: ${temperature}
       max_new_tokens: ${max_new_tokens}
-      streaming: ${streaming}
+      streaming: false
       tools: /home/user/tools/supervisor_agent_tools.yaml
       require_human_feedback: false
       no_proxy: ${no_proxy}

AgentQnA/docker_compose/intel/cpu/xeon/launch_agent_service_openai.sh

@@ -1,13 +1,16 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
+export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
 export ip_address=$(hostname -I | awk '{print $1}')
-export recursion_limit=12
+export recursion_limit_worker=12
+export recursion_limit_supervisor=10
 export model="gpt-4o-mini-2024-07-18"
 export temperature=0
 export max_new_tokens=512
 export OPENAI_API_KEY=${OPENAI_API_KEY}
 export WORKER_AGENT_URL="http://${ip_address}:9095/v1/chat/completions"
+export RETRIEVAL_TOOL_URL="http://${ip_address}:8889/v1/retrievaltool"
 export CRAG_SERVER=http://${ip_address}:8080
 
 docker compose -f compose_openai.yaml up -d

AgentQnA/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -0,0 +1,94 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  tgi-server:
+    image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+    container_name: tgi-server
+    ports:
+      - "8085:80"
+    volumes:
+      - ${HF_CACHE_DIR}:/data
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_HUB_DISABLE_PROGRESS_BARS: 1
+      HF_HUB_ENABLE_HF_TRANSFER: 0
+      HABANA_VISIBLE_DEVICES: all
+      OMPI_MCA_btl_vader_single_copy_mechanism: none
+      PT_HPU_ENABLE_LAZY_COLLECTIVES: true
+    runtime: habana
+    cap_add:
+      - SYS_NICE
+    ipc: host
+    command: --model-id ${LLM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192 --sharded true --num-shard ${NUM_SHARDS}
+  worker-docgrader-agent:
+    image: opea/comps-agent-langchain:latest
+    container_name: docgrader-agent-endpoint
+    depends_on:
+      - tgi-server
+    volumes:
+      # - ${WORKDIR}/GenAIExamples/AgentQnA/docker_image_build/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
+      - ${TOOLSET_PATH}:/home/user/tools/
+    ports:
+      - "9095:9095"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: rag_agent
+      recursion_limit: ${recursion_limit_worker}
+      llm_engine: tgi
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      llm_endpoint_url: ${LLM_ENDPOINT_URL}
+      model: ${LLM_MODEL_ID}
+      temperature: ${temperature}
+      max_new_tokens: ${max_new_tokens}
+      streaming: false
+      tools: /home/user/tools/worker_agent_tools.yaml
+      require_human_feedback: false
+      RETRIEVAL_TOOL_URL: ${RETRIEVAL_TOOL_URL}
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
+      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
+      LANGCHAIN_PROJECT: "opea-worker-agent-service"
+      port: 9095
+
+
+  supervisor-react-agent:
+    image: opea/comps-agent-langchain:latest
+    container_name: react-agent-endpoint
+    depends_on:
+      - tgi-server
+      - worker-docgrader-agent
+    volumes:
+      # - ${WORKDIR}/GenAIExamples/AgentQnA/docker_image_build/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
+      - ${TOOLSET_PATH}:/home/user/tools/
+    ports:
+      - "9090:9090"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: react_langgraph
+      recursion_limit: ${recursion_limit_supervisor}
+      llm_engine: tgi
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      llm_endpoint_url: ${LLM_ENDPOINT_URL}
+      model: ${LLM_MODEL_ID}
+      temperature: ${temperature}
+      max_new_tokens: ${max_new_tokens}
+      streaming: false
+      tools: /home/user/tools/supervisor_agent_tools.yaml
+      require_human_feedback: false
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
+      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
+      LANGCHAIN_PROJECT: "opea-supervisor-agent-service"
+      CRAG_SERVER: $CRAG_SERVER
+      WORKER_AGENT_URL: $WORKER_AGENT_URL
+      port: 9090

AgentQnA/docker_compose/intel/hpu/gaudi/launch_agent_service_tgi_gaudi.sh

@@ -0,0 +1,43 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+WORKPATH=$(dirname "$PWD")/..
+# export WORKDIR=$WORKPATH/../../
+echo "WORKDIR=${WORKDIR}"
+export ip_address=$(hostname -I | awk '{print $1}')
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+
+# LLM related environment variables
+export HF_CACHE_DIR=${HF_CACHE_DIR}
+ls $HF_CACHE_DIR
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export LLM_MODEL_ID="meta-llama/Meta-Llama-3.1-70B-Instruct"
+export NUM_SHARDS=4
+export LLM_ENDPOINT_URL="http://${ip_address}:8085"
+export temperature=0.01
+export max_new_tokens=512
+
+# agent related environment variables
+export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
+echo "TOOLSET_PATH=${TOOLSET_PATH}"
+export recursion_limit_worker=12
+export recursion_limit_supervisor=10
+export WORKER_AGENT_URL="http://${ip_address}:9095/v1/chat/completions"
+export RETRIEVAL_TOOL_URL="http://${ip_address}:8889/v1/retrievaltool"
+export CRAG_SERVER=http://${ip_address}:8080
+
+docker compose -f compose.yaml up -d
+
+sleep 5s
+echo "Waiting tgi gaudi ready"
+n=0
+until [[ "$n" -ge 100 ]] || [[ $ready == true ]]; do
+    docker logs tgi-server &> tgi-gaudi-service.log
+    n=$((n+1))
+    if grep -q Connected tgi-gaudi-service.log; then
+        break
+    fi
+    sleep 5s
+done
+sleep 5s
+echo "Service started successfully"

AgentQnA/docker_image_build/build.yaml

@@ -0,0 +1,13 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  agent-endpoint:
+    build:
+      context: GenAIComps
+      dockerfile: comps/agent/langchain/Dockerfile
+      args:
+        http_proxy: ${http_proxy}
+        https_proxy: ${https_proxy}
+        no_proxy: ${no_proxy}
+    image: ${REGISTRY:-opea}/comps-agent-langchain:${TAG:-latest}