Merge branch 'main' into multi-turn-v1.3

.github/workflows/_comps-workflow.yml

@@ -71,7 +71,6 @@ jobs:
           fi
           if [[ $(grep -c "vllm-gaudi:" ${docker_compose_yml}) != 0 ]]; then
               git clone --depth 1 --branch v0.6.4.post2+Gaudi-1.19.0 https://github.com/HabanaAI/vllm-fork.git
-              sed -i 's/triton/triton==3.1.0/g' vllm-fork/requirements-hpu.txt
           fi
       - name: Get build list
         id: get-build-list

.github/workflows/_run-helm-chart.yml

@@ -134,8 +134,9 @@ jobs:
           if [[ "${service,,}" == *"third_parties"* ]]; then
             CHART_NAME="$(echo "${service,,}"|cut -d'/' -f2)"  # bridgetower
           else
-            CHART_NAME="${service_name}"  # agent
+            CHART_NAME="${service_name}"  # web_retrievers
           fi
+          CHART_NAME=$(echo "$CHART_NAME" | tr -cd 'a-z0-9')
           echo "service_name=$service_name" >> $GITHUB_ENV
           echo "CHART_NAME=$CHART_NAME" >> $GITHUB_ENV
           echo "RELEASE_NAME=${CHART_NAME}$(date +%d%H%M%S)" >> $GITHUB_ENV

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

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

.github/workflows/manual-comps-test.yml

@@ -7,7 +7,7 @@ on:
     inputs:
       services:
         default: "asr"
-        description: "List of services to test [agent,asr,chathistory,dataprep,embeddings,feedback_management,finetuning,guardrails,knowledgegraphs,llms,lvms,nginx,prompt_registry,ragas,rerankings,retrievers,tts,web_retrievers]"
+        description: "List of services to test [agent,asr,chathistory,animation,dataprep,embeddings,feedback_management,finetuning,guardrails,image2image,image2video,intent_detection,llms,lvms,prompt_registry,ragas,rerankings,retrievers,text2image,text2sql,third_parties,tts,vectorstores,web_retrievers]"
         required: true
         type: string
       build:

.github/workflows/manual-docker-publish.yml

@@ -7,7 +7,7 @@ on:
     inputs:
       services:
         default: ""
-        description: "List of services to test [agent,asr,chathistory,dataprep,embeddings,feedback_management,finetuning,guardrails,knowledgegraphs,llms,lvms,nginx,prompt_registry,ragas,rerankings,retrievers,tts,web_retrievers]"
+        description: "List of services to test [agent,asr,chathistory,animation,dataprep,embeddings,feedback_management,finetuning,guardrails,image2image,image2video,intent_detection,llms,lvms,prompt_registry,ragas,rerankings,retrievers,text2image,text2sql,third_parties,tts,vectorstores,web_retrievers]"
         required: false
         type: string
       images:

.github/workflows/push-image-build.yml

@@ -62,7 +62,7 @@ jobs:
 
   image-build:
     needs: get-build-matrix
-    if: ${{ fromJSON(needs.get-build-matrix.outputs.services).length != 0 }}
+    if: needs.get-build-matrix.outputs.services != '[]'
     strategy:
       matrix:
         service: ${{ fromJSON(needs.get-build-matrix.outputs.services) }}
@@ -96,7 +96,6 @@ jobs:
           fi
           if [[ $(grep -c "vllm-gaudi:" ${docker_compose_path}) != 0 ]]; then
               git clone --depth 1 --branch v0.6.4.post2+Gaudi-1.19.0 https://github.com/HabanaAI/vllm-fork.git
-              sed -i 's/triton/triton==3.1.0/g' vllm-fork/requirements-hpu.txt
           fi
 
       - name: Build Image

Dockerfile

@@ -0,0 +1,37 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# Base image for GenAIComps based OPEA Python applications
+# Build: docker build -t opea/comps-base -f Dockerfile .
+
+ARG IMAGE_NAME=python
+ARG IMAGE_TAG=3.11-slim
+
+FROM ${IMAGE_NAME}:${IMAGE_TAG} AS base
+
+ENV HOME=/home/user
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p $HOME && \
+    chown -R user $HOME
+
+# get security updates
+RUN apt-get update && apt-get upgrade -y && \
+    apt-get clean autoclean && \
+    apt-get autoremove -y && \
+    rm -rf /var/lib/apt/lists/*
+
+WORKDIR $HOME
+
+COPY *.toml *.py *.txt *.md LICENSE ./
+
+RUN pip install --no-cache-dir --upgrade pip setuptools && \
+    pip install --no-cache-dir -r requirements.txt
+
+COPY comps/ comps/
+
+ENV PYTHONPATH=$PYTHONPATH:$HOME
+
+USER user
+
+ENTRYPOINT ["sh", "-c", "set && ls -la"]

LEGAL_INFORMATION.md

@@ -13,6 +13,9 @@ Your use of the source code for these components is subject to the terms and con
 
 See the accompanying [license](LICENSE) file for full license text and copyright notices.
 
+Please note: component(s) depend on software subject to non-open source licenses.  If you use or redistribute this software, it is your sole responsibility to ensure compliance with such licenses.
+e.g langserve
+
 ## Citation
 
 If you use Generative AI Components in your research, use the following BibTeX entry.

comps/chathistory/deployment/docker_compose/compose.yaml

@@ -15,7 +15,7 @@ services:
     command: mongod --quiet --logpath /dev/null
 
   chathistory-mongo:
-    image: ${REGISTRY:-opea}/chathistory-mongo-server:${TAG:-latest}
+    image: ${REGISTRY:-opea}/chathistory-mongo:${TAG:-latest}
     container_name: chathistory-mongo-server
     ports:
       - "${CHATHISTORY_PORT:-6012}:6012"

comps/chathistory/src/README.md

@@ -23,7 +23,7 @@ export COLLECTION_NAME=${COLLECTION_NAME}
 
 ```bash
 cd ../../../../
-docker build -t opea/chathistory-mongo-server:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/chathistory/src/Dockerfile .
+docker build -t opea/chathistory-mongo:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/chathistory/src/Dockerfile .
 ```
 
 ### Run Docker with CLI

comps/cores/mega/orchestrator.py

@@ -7,6 +7,7 @@
 import json
 import os
 import re
+import threading
 import time
 from typing import Dict, List
 
@@ -27,28 +28,64 @@
 
 
 class OrchestratorMetrics:
-    # Because:
-    # - CI creates several orchestrator instances
-    # - Prometheus requires metrics to be singletons
-    # - Oorchestror instances are not provided their own names
-    # Metrics are class members with "megaservice" name prefix
-    first_token_latency = Histogram("megaservice_first_token_latency", "First token latency (histogram)")
-    inter_token_latency = Histogram("megaservice_inter_token_latency", "Inter-token latency (histogram)")
-    request_latency = Histogram("megaservice_request_latency", "Whole request/reply latency (histogram)")
-    request_pending = Gauge("megaservice_request_pending", "Count of currently pending requests (gauge)")
+    # Need an static class-level ID for metric prefix because:
+    # - Prometheus requires metrics (their names) to be unique
+    _instance_id = 0
 
     def __init__(self) -> None:
-        pass
+        OrchestratorMetrics._instance_id += 1
+        if OrchestratorMetrics._instance_id > 1:
+            self._prefix = f"megaservice{self._instance_id}"
+        else:
+            self._prefix = "megaservice"
+
+        self.request_pending = Gauge(f"{self._prefix}_request_pending", "Count of currently pending requests (gauge)")
+
+        # locking for latency metric creation / method change
+        self._lock = threading.Lock()
+
+        # Metrics related to token processing are created on demand,
+        # to avoid bogus ones for services that never handle tokens
+        self.first_token_latency = None
+        self.inter_token_latency = None
+        self.request_latency = None
+
+        # initial methods to create the metrics
+        self.token_update = self._token_update_create
+        self.request_update = self._request_update_create
+
+    def _token_update_create(self, token_start: float, is_first: bool) -> float:
+        with self._lock:
+            # in case another thread already got here
+            if self.token_update == self._token_update_create:
+                self.first_token_latency = Histogram(
+                    f"{self._prefix}_first_token_latency", "First token latency (histogram)"
+                )
+                self.inter_token_latency = Histogram(
+                    f"{self._prefix}_inter_token_latency", "Inter-token latency (histogram)"
+                )
+                self.token_update = self._token_update_real
+        return self.token_update(token_start, is_first)
+
+    def _request_update_create(self, req_start: float) -> None:
+        with self._lock:
+            # in case another thread already got here
+            if self.request_update == self._request_update_create:
+                self.request_latency = Histogram(
+                    f"{self._prefix}_request_latency", "Whole LLM request/reply latency (histogram)"
+                )
+                self.request_update = self._request_update_real
+        self.request_update(req_start)
 
-    def token_update(self, token_start: float, is_first: bool) -> float:
+    def _token_update_real(self, token_start: float, is_first: bool) -> float:
         now = time.time()
         if is_first:
             self.first_token_latency.observe(now - token_start)
         else:
             self.inter_token_latency.observe(now - token_start)
         return now
 
-    def request_update(self, req_start: float) -> None:
+    def _request_update_real(self, req_start: float) -> None:
         self.request_latency.observe(time.time() - req_start)
 
     def pending_update(self, increase: bool) -> None:

comps/dataprep/deployment/docker_compose/compose.yaml

@@ -28,7 +28,7 @@ services:
       DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_ELASTICSEARCH"
       ES_CONNECTION_STRING: ${ES_CONNECTION_STRING}
       INDEX_NAME: ${INDEX_NAME}
-      TEI_ENDPOINT: ${TEI_ENDPOINT}
+      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
       HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     restart: unless-stopped
     depends_on:
@@ -49,6 +49,7 @@ services:
       MILVUS_HOST: ${MILVUS_HOST}
       TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
       HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+      LOGFLAG: ${LOGFLAG}
     restart: unless-stopped
     depends_on:
       tei-embedding-serving:
@@ -161,7 +162,7 @@ services:
       QDRANT_HOST: ${QDRANT_HOST}
       QDRANT_PORT: ${QDRANT_PORT}
       COLLECTION_NAME: ${COLLECTION_NAME}
-      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
+      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
       HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     restart: unless-stopped
 

comps/dataprep/src/README_elasticsearch.md

@@ -50,7 +50,7 @@ docker build -t opea/dataprep:latest --build-arg https_proxy=$https_proxy --buil
 ### 2.4 Run Docker with CLI (Option A)
 
 ```bash
-docker run  --name="dataprep-elasticsearch" -p 6011:6011 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e ES_CONNECTION_STRING=$ES_CONNECTION_STRING  -e INDEX_NAME=$INDEX_NAME -e TEI_ENDPOINT=$TEI_ENDPOINT -e DATAPREP_COMPONENT_NAME="OPEA_DATAPREP_ELASTICSEARCH" opea/dataprep:latest
+docker run  --name="dataprep-elasticsearch" -p 6011:6011 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e ES_CONNECTION_STRING=$ES_CONNECTION_STRING  -e INDEX_NAME=$INDEX_NAME -e TEI_EMBEDDING_ENDPOINT=$TEI_EMBEDDING_ENDPOINT -e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN -e DATAPREP_COMPONENT_NAME="OPEA_DATAPREP_ELASTICSEARCH" opea/dataprep:latest
 ```
 
 ### 2.5 Run with Docker Compose (Option B)

comps/dataprep/src/README_milvus.md

@@ -25,6 +25,7 @@ export MILVUS_HOST=${your_milvus_host_ip}
 export MILVUS_PORT=19530
 export COLLECTION_NAME=${your_collection_name}
 export TEI_EMBEDDING_ENDPOINT=${your_embedding_endpoint}
+export HUGGINGFACEHUB_API_TOKEN=${your_huggingface_api_token}
 ```
 
 ### 1.4 Start TEI Embedding Service
@@ -70,13 +71,15 @@ docker build -t opea/dataprep:latest --build-arg https_proxy=$https_proxy --buil
 
 ```bash
 export TEI_EMBEDDING_ENDPOINT="http://localhost:$your_port"
+export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
+export EMBEDDING_MODEL_ID=${your_embedding_model_id}
 export MILVUS_HOST=${your_host_ip}
 ```
 
 ### 2.3 Run Docker with CLI (Option A)
 
 ```bash
-docker run -d --name="dataprep-milvus-server" -p 6010:6010 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e no_proxy=$no_proxy -e TEI_EMBEDDING_ENDPOINT=${TEI_EMBEDDING_ENDPOINT} -e MILVUS_HOST=${MILVUS_HOST} -e DATAPREP_COMPONENT_NAME="OPEA_DATAPREP_MILVUS" opea/dataprep:latest
+docker run -d --name="dataprep-milvus-server" -p 6010:6010 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e no_proxy=$no_proxy -e TEI_EMBEDDING_ENDPOINT=${TEI_EMBEDDING_ENDPOINT} -e MILVUS_HOST=${MILVUS_HOST} -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e DATAPREP_COMPONENT_NAME="OPEA_DATAPREP_MILVUS" opea/dataprep:latest
 ```
 
 ### 2.4 Run with Docker Compose (Option B)

comps/dataprep/src/README_opensearch.md

@@ -51,7 +51,7 @@ curl localhost:$your_port/embed \
 After checking that it works, set up environment variables.
 
 ```bash
-export TEI_ENDPOINT="http://localhost:$your_port"
+export TEI_EMBEDDING_ENDPOINT="http://localhost:$your_port"
 ```
 
 ### 1.4 Start Document Preparation Microservice for OpenSearch with Python Script
@@ -75,7 +75,7 @@ Please refer to this [readme](../../third_parties/opensearch/src/README.md).
 
 ```bash
 export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export TEI_ENDPOINT="http://${your_ip}:6006"
+export TEI_EMBEDDING_ENDPOINT="http://${your_ip}:6006"
 export OPENSEARCH_URL="http://${your_ip}:9200"
 export INDEX_NAME=${your_index_name}
 export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
@@ -97,7 +97,7 @@ docker build -t opea/dataprep:latest --build-arg https_proxy=$https_proxy --buil
 - option 1: Start single-process version (for processing up to 10 files)
 
 ```bash
-docker run -d --name="dataprep-opensearch-server" -p 6007:6007 --runtime=runc --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e OPENSEARCH_URL=$OPENSEARCH_URL -e INDEX_NAME=$INDEX_NAME -e TEI_ENDPOINT=$TEI_ENDPOINT -e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN -e DATAPREP_COMPONENT_NAME="OPEA_DATAPREP_OPENSEARCH" opea/dataprep:latest
+docker run -d --name="dataprep-opensearch-server" -p 6007:6007 --runtime=runc --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e OPENSEARCH_URL=$OPENSEARCH_URL -e INDEX_NAME=$INDEX_NAME -e EMBED_MODEL=${EMBED_MODEL} -e TEI_EMBEDDING_ENDPOINT=$TEI_EMBEDDING_ENDPOINT -e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN -e DATAPREP_COMPONENT_NAME="OPEA_DATAPREP_OPENSEARCH" opea/dataprep:latest
 ```
 
 ### 2.5 Run with Docker Compose (Option B - deprecated, will move to genAIExample in future)

comps/dataprep/src/README_pgvector.md

@@ -38,6 +38,8 @@ Please refer to this [readme](../../third_parties/pgvector/src/README.md).
 ```bash
 export PG_CONNECTION_STRING=postgresql+psycopg2://testuser:testpwd@${your_ip}:5432/vectordb
 export INDEX_NAME=${your_index_name}
+export TEI_EMBEDDING_ENDPOINT=${your_tei_embedding_endpoint}
+export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
 ```
 
 ### 2.3 Build Docker Image
@@ -50,7 +52,7 @@ docker build -t opea/dataprep:latest --build-arg https_proxy=$https_proxy --buil
 ### 2.4 Run Docker with CLI (Option A)
 
 ```bash
-docker run  --name="dataprep-pgvector" -p 6007:6007 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e PG_CONNECTION_STRING=$PG_CONNECTION_STRING  -e INDEX_NAME=$INDEX_NAME -e TEI_ENDPOINT=$TEI_ENDPOINT -e DATAPREP_COMPONENT_NAME="OPEA_DATAPREP_PGVECTOR" opea/dataprep:latest
+docker run  --name="dataprep-pgvector" -p 6007:6007 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e PG_CONNECTION_STRING=$PG_CONNECTION_STRING  -e INDEX_NAME=$INDEX_NAME -e EMBED_MODEL=${EMBED_MODEL} -e TEI_EMBEDDING_ENDPOINT=$TEI_EMBEDDING_ENDPOINT -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e DATAPREP_COMPONENT_NAME="OPEA_DATAPREP_PGVECTOR" opea/dataprep:latest
 ```
 
 ### 2.5 Run with Docker Compose (Option B)

comps/dataprep/src/README_redis.md

@@ -95,8 +95,7 @@ Please refer to this [readme](../../third_parties/redis/src/README.md).
 ### 2.2 Setup Environment Variables
 
 ```bash
-export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export TEI_ENDPOINT="http://${your_ip}:6006"
+export TEI_EMBEDDING_ENDPOINT="http://${your_ip}:6006"
 export REDIS_URL="redis://${your_ip}:6379"
 export INDEX_NAME=${your_index_name}
 export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
@@ -112,7 +111,7 @@ docker build -t opea/dataprep:latest --build-arg https_proxy=$https_proxy --buil
 ### 2.4 Run Docker with CLI (Option A)
 
 ```bash
-docker run -d --name="dataprep-redis-server" -p 6007:6007 --runtime=runc --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e REDIS_URL=$REDIS_URL -e INDEX_NAME=$INDEX_NAME -e TEI_ENDPOINT=$TEI_ENDPOINT -e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN opea/dataprep:latest
+docker run -d --name="dataprep-redis-server" -p 6007:5000 --runtime=runc --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e REDIS_URL=$REDIS_URL -e INDEX_NAME=$INDEX_NAME -e TEI_EMBEDDING_ENDPOINT=$TEI_EMBEDDING_ENDPOINT -e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN opea/dataprep:latest
 ```
 
 ### 2.5 Run with Docker Compose (Option B - deprecated, will move to genAIExample in future)

comps/dataprep/src/README_vdms.md

@@ -69,7 +69,8 @@ export http_proxy=${your_http_proxy}
 export https_proxy=${your_http_proxy}
 export VDMS_HOST=${host_ip}
 export VDMS_PORT=55555
-export TEI_ENDPOINT=${your_tei_endpoint}
+export TEI_EMBEDDING_ENDPOINT=${your_tei_endpoint}
+export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
 export COLLECTION_NAME=${your_collection_name}
 export SEARCH_ENGINE="FaissFlat"
 export DISTANCE_STRATEGY="L2"
@@ -89,7 +90,8 @@ Start single-process version (for 1-10 files processing)
 
 ```bash
 docker run -d --name="dataprep-vdms-server" -p 6007:6007 --runtime=runc --ipc=host \
--e http_proxy=$http_proxy -e https_proxy=$https_proxy -e TEI_ENDPOINT=$TEI_ENDPOINT \
+-e http_proxy=$http_proxy -e https_proxy=$https_proxy \
+-e TEI_EMBEDDING_ENDPOINT=$TEI_EMBEDDING_ENDPOINT -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} \
 -e COLLECTION_NAME=$COLLECTION_NAME -e VDMS_HOST=$VDMS_HOST -e VDMS_PORT=$VDMS_PORT \
 -e DATAPREP_COMPONENT_NAME="OPEA_DATAPREP_VDMS" opea/dataprep:latest
 ```