# OPEA Release Notes v1.3 We are excited to announce the release of OPEA version 1.3, which includes significant contributions from the open-source community. This release addresses over 520 pull requests. More information about how to get started with OPEA v1.3 can be found on the [Getting Started](https://opea-project.github.io/latest/index.html) page. All project source code is maintained in the [opea-project organization](https://github.com/opea-project). To pull Docker images, please access the [Docker Hub](https://hub.docker.com/u/opea). For instructions on deploying Helm Charts, please refer to the [guide](https://github.com/opea-project/GenAIInfra/tree/v1.3/helm-charts#readme). ## Table of Contents - [What's New in OPEA v1.3](#whats-new-in-opea-v13) - [Deprecations](#deprecations) - [Updated Dependencies](#updated-dependencies) - [Changes to Default Behavior](#changes-to-default-behavior) - [Validated Hardware](#validated-hardware) - [Validated Software](#validated-software) - [Known Issues](#known-issues) - [Full Changelogs](#full-changelogs) - [Contributors](#contributors) ## What's New in OPEA v1.3 This release introduces exciting capabilities, optimizations, and user-centric enhancements: ### Advanced Agent Capabilities - Multi-Turn Conversation: Enhanced the OPEA agent framework for dynamic, context-aware dialogues. ([GenAIComps#1248](https://github.com/opea-project/GenAIComps/pull/1248)) - Finance Agent Example: A financial agent [example](https://github.com/opea-project/GenAIExamples/tree/v1.3/FinanceAgent) for automating financial data aggregation and leveraging LLMs to generate insights, forecasts, and strategic recommendations. ([GenAIExamples#](https://github.com/opea-project/GenAIExamples/pull/1539)) ### Performance and Scalability - vLLM Enhancement: Integrated [vLLM](https://github.com/vllm-project/vllm) as the default LLM serving backend for key GenAI examples across Intel® Xeon® processors, Intel® Gaudi® accelerators, and AMD® GPUs. ([GenAIExamples#](https://github.com/opea-project/GenAIExamples/pull/1436)) - KubeAI Operator for OPEA (Alpha release): Simplified OPEA inference operations in cloud environment and enabled optimal out-of-the-box performance for specific models and hardware using profiles. ([GenAIInfra#945](https://github.com/opea-project/GenAIInfra/pull/945)) ### Ecosystem Integrations - Haystack Integration: Enabled OPEA as a backend of [Haystack](https://haystack.deepset.ai). ([Haystack-OPEA#](https://github.com/opea-project/Haystack-OPEA#)) - Cloud Readiness: Expanded automated Terraform deployment for ChatQnA to include support for Azure, and enabled CodeGen deployments on AWS and GCP. ([GenAIExamples#1731](https://github.com/opea-project/GenAIExamples/pull/1731)) ### New GenAI Capabilities - OPEA Store: Delivered a unified data store access API and a robust data store integration layer that streamlines data store integration. ArangoDB was integrated. ([GenAIComps#1493](https://github.com/opea-project/GenAIComps/pull/1493)) - CodeGen using RAG and Agent: Leveraged RAG and code agent to provide an additional layer of intelligence and adaptability for CodeGen example. ([GenAIExamples#1757](https://github.com/opea-project/GenAIExamples/pull/1757)) - Enhanced Multimodality: Added support for additional audio file types (.mp3) and supported spoken audio captions with image ingestion. ([GenAIExamples#1549](https://github.com/opea-project/GenAIExamples/issues/1549)) - Struct to Graph: Supported transforming structured data to graphs using Neo4j graph database. ([GenAIComps#1502](https://github.com/opea-project/GenAIComps/pull/1502)) - Text to Graph: Supported creating graphs from text by extracting graph triplets. ([GenAIComps#1357](https://github.com/opea-project/GenAIComps/pull/1357), [GenAIComps#](https://github.com/opea-project/GenAIComps/pull/1472)) - Text to Cypher: Supported generating and executing Cypher queries from natural language for graph database retrieval. ([GenAIComps#1319](https://github.com/opea-project/GenAIComps/pull/1319)) ### Enhanced Evaluation - Enhanced Long-Context Model Evaluation: Supported evaluating long-context model on Intel® Gaudi® with vLLM. ([HELMET#20](https://github.com/princeton-nlp/HELMET/pull/20)) - TAG-Bench for SQL Agents: Integrated [TAG-Bench](https://github.com/TAG-Research/TAG-Bench) to evaluate complex SQL query generation ([GenAIEval#](https://github.com/opea-project/GenAIEval/pull/230)). - DocSum Support: GenAIEval now supports evaluating the performance of DocSum. ([GenAIEval#252](https://github.com/opea-project/GenAIEval/pull/252)) - Toxicity Detection Evaluation: Introduced a workflow to evaluate the capability of detecting toxic language based on LLMs. ([GenAIEval#241](https://github.com/opea-project/GenAIEval/pull/241)) - Model Card: Added a model card generator for generating reports containing model performance and fairness metrics. ([GenAIEval#236](https://github.com/opea-project/GenAIEval/pull/236)) ### Observability - OpenTelemetry Tracing: Leveraged OpenTelemetry to enable tracing for ChatQnA and AgentQnA along with TGI and TEI. ([GenAIExamples#1542](https://github.com/opea-project/GenAIExamples/issues/1542)) - Application dashboards: Helm installed application E2E performance dashboard(s). ([GenAIInfra#800](https://github.com/opea-project/GenAIInfra/pull/800)) - E2E (end-to-end) metric improvements: E2E metrics are summed together for applications that use multiple megaservice instances. Tests for the E2E metrics + fixes. ([GenAIComps#1301](https://github.com/opea-project/GenAIComps/pull/1301), ([GenAIComps#](https://github.com/opea-project/GenAIComps/pull/1343)) ### Better User Experience - GenAIStudio: Supported drag-and-drop creation of agentic applications. ([GenAIStudio#50](https://github.com/opea-project/GenAIStudio/pull/50)) - Documentation Refinement: Refined READMEs for key examples to help readers easily locate documentation tailored to deployment, customization, and hardware. ([GenAIExamples#1741](https://github.com/opea-project/GenAIExamples/issues/1741)) - Optimized Dockerfiles: Simplified application Dockerfiles for faster image builds. ([GenAIExamples#1585](https://github.com/opea-project/GenAIExamples/pull/1585)) ### Exploration - SQFT: Supported low-precision sparse parameter-efficient fine-tuning on LLMs. ([GenAIResearch#1](https://github.com/opea-project/GenAIResearch/pull/1)) ### Newly Supported Models OPEA introduced the support for the following models in this release. | Model | TGI-Gaudi | vLLM-CPU | vLLM-Gaudi | vLLM-ROCm | OVMS | Optimum-Habana | PredictionGuard | | ------------------------------------------- | --------- | -------- | ---------- | --------- | -------- | -------------- | --------------- | | deepseek-ai/DeepSeek-R1-Distill-Llama-8B | ✓ | ✓ | ✓ | ✓ | - | ✓ | - | | deepseek-ai/DeepSeek-R1-Distill-Llama-70B | ✓ | ✓ | ✓ | ✓ | - | ✓ | - | | deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | ✓ | ✓ | ✓ | ✓ | - | ✓ | - | | deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | ✓ | ✓ | ✓ | ✓ | - | ✓ | - | | deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | ✓ | ✓ | ✓ | ✓ | - | ✓ | - | | deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | ✓ | ✓ | ✓ | ✓ | - | ✓ | - | | deepseek-ai/Deepseek-v3 | ✓ | - | ✓ | ✓ | - | ✓ | - | | Hermes-3-Llama-3.1-8B | - | - | - | ✓ | - | - | ✓ | | ibm-granite/granite-3.2-8b-instruct | - | - | ✓ | ✓ | - | - | - | | Phi-4-mini | x | x | x | ✓ | x | ✓ | - | | Phi-4-multimodal-instruct | x | x | x | ✓ | x | ✓ | - | | mistralai/Mistral-Small-24B-Instruct-2501 | ✓ | - | ✓ | ✓ | - | ✓ | - | | mistralai/Mistral-Large-Instruct-2411 | x | - | ✓ | ✓ | - | ✓ | - | (✓: supported; -: not validated; x: unsupported) ### Newly Supported Hardware - AMD® GPU using AMD® ROCm™ for 9 examples. ([GenAIExamples#1613](https://github.com/opea-project/GenAIExamples/pull/1613) and 8 more.) ### Other Notable Changes Expand the following lists to read:
GenAIExamples - Functionalities - [AgentQnA] Added web search tool support and simplify the run instructions. ([#1656](https://github.com/opea-project/GenAIExamples/pull/1656)) (e8f2313) - [ChatQnA] Added support for latest deepseek models on Gaudi ([#1491](https://github.com/opea-project/GenAIExamples/pull/1491)) (9adf7a6) - [EdgeCraftRAG] A sleek new UI based on Vue and Ant Design for enhanced user experience, supporting concurrent multi-requests on vLLM, JSON pipeline configuration, and API-based prompt modification. ([#1665](https://github.com/opea-project/GenAIExamples/pull/1665)) (5a50ae0) - [EdgeCraftRAG] Supported multi-card deployment of Intel ARC GPU for vllm inference ([#1729](https://github.com/opea-project/GenAIExamples/pull/1729)) (1a0c5f0) - [FaqGen] Merged FaqGen into ChatQnA for unified Chatbot experience. ([#1654](https://github.com/opea-project/GenAIExamples/pull/1654)) (6d24c1c) - Benchmark - [ChatQnA] Provided unified scalable deployment and benchmarking support for examples ([#1315](https://github.com/opea-project/GenAIExamples/pull/1315)) (ed16308) - Deployment - Sync values yaml file for 1.3 release ([#1748](https://github.com/opea-project/GenAIExamples/pull/1748)) (46ebb78) - Bug Fixes - [AgentQnA] Fixed errors for running AgentQnA on xeon with openai and update readme ([#1664](https://github.com/opea-project/GenAIExamples/pull/1664)) (fecc227) - [AudioQnA] Fixed the LLM model field for inputs alignment ([#1611](https://github.com/opea-project/GenAIExamples/pull/1611)) (2dfcfa0) - Documentation - Updated README.md for OPEA OTLP tracing ([#1406](https://github.com/opea-project/GenAIExamples/pull/1406)) (4c41a5d) - Updated README.md for Agent UI ([#1495](https://github.com/opea-project/GenAIExamples/pull/1495)) (88a8235) - Refactored AudioQnA README ([#1508](https://github.com/opea-project/GenAIExamples/pull/1508)) (9f36e84) - Added a new section to change LLM model such as deepseek based on validated model table in LLM microservice ([#1501](https://github.com/opea-project/GenAIExamples/pull/1501)) (970b869) - Updated README.md of AIPC quick start ([#1578](https://github.com/opea-project/GenAIExamples/pull/1578)) (852bc70) - Added short descriptions to the images OPEA publishes on Docker Hub ([#1637](https://github.com/opea-project/GenAIExamples/pull/1637)) (68747a9) - CI/CD/UT - Added UT for rerank finetuning on Gaudi ([#1472](https://github.com/opea-project/GenAIExamples/pull/1472)) (5f4b182) - Enabled Gaudi 3, Rocm and Arc on manually release test. ([#1615](https://github.com/opea-project/GenAIExamples/pull/1615)) (63b789a) - Enabled base image build in CI/CD ([#1669](https://github.com/opea-project/GenAIExamples/pull/1669)) (2204fe8) - ChatQnA run CI with latest base image, group logs in GHA outputs. ([#1736](https://github.com/opea-project/GenAIExamples/pull/1736)) (c48cd65)
GenAIComps - Functionalities - [agent] Enabled custom prompt for react_llama and react_langgraph ([#1391](https://github.com/opea-project/GenAIComps/pull/1391)) (558a2f6) - [dataprep] Added Multimodal support for Milvus for dataprep component ([#1380](https://github.com/opea-project/GenAIComps/pull/1380)) (006bd91) - [dataprep]: New Arango integration ([#1558](https://github.com/opea-project/GenAIComps/pull/1558)) - [dataprep]: Added ability to customize Dataprep unique input parameters by way of subclassing the DataprepRequest pydantic model. Avoids having to introduce parameters unique to a few Dataprep integrations across all Dataprep providers ([#1525](https://github.com/opea-project/GenAIComps/pull/1525)) - [retrieval]: New Arango integration ([#1558](https://github.com/opea-project/GenAIComps/pull/1558)) - [cores/mega] Added remote endpoint support ([#1399](https://github.com/opea-project/GenAIComps/pull/1399)) (1871dec) - [docsum] Enlarged DocSum prompt buffer ([#1471](https://github.com/opea-project/GenAIComps/pull/1471)) (772ef6e) - [embeddings] Refined CLIP embedding microservice by leveraging the third-party CLIP ([#1298](https://github.com/opea-project/GenAIComps/pull/1298)) (7727235) - [finetuning] Added xtune to finetuning for Intel ARC GPU ([#1432](https://github.com/opea-project/GenAIComps/pull/1432)) (80ef317) - [guardrails] Added native support for toxicity detection guardrail microservice ([#1258](https://github.com/opea-project/GenAIComps/pull/1258)) (625aec9) - [llm/text-generation] Added support for string message in Bedrock textgen ([#1291](https://github.com/opea-project/GenAIComps/pull/1291)) (364ccad) - [ipex] Added native LLM microservice using IPEX ([#1337](https://github.com/opea-project/GenAIComps/pull/1337)) (d51a136) - [lvm] Integrated vLLM to lvm as a backend ([#1362](https://github.com/opea-project/GenAIComps/pull/1362)) (831c5a3) - [lvm] Integrated UI-TARS vLLM in lvm component ([#1458](https://github.com/opea-project/GenAIComps/pull/1458)) (4a15795) - [nubula] Docker deployment support for Nebula graph database ([#1396](https://github.com/opea-project/GenAIComps/pull/1396)) (342c1ed) - [OVMS] Text generation, Embeddings and Reranking microservices based on [OVMS](https://github.com/openvinotoolkit/model_server) component ([#](https://github.com/opea-project/GenAIComps/pull/1318)) (78b94fc) - [retriever/milvus] Added Multimodal support for Milvus for retriever component ([#1381](https://github.com/opea-project/GenAIComps/pull/1381)) (40d431a) - [text2image & image2image] Enriched input parameters of text2image and image2image. ([#1339](https://github.com/opea-project/GenAIComps/pull/1339)) (42f323f) - Refined synchronized I/O in asynchronous functions ([#1300](https://github.com/opea-project/GenAIComps/pull/1300)) (b08571f) - Bug Fixes - Docsum error by HuggingFaceEndpoint ([#1246](https://github.com/opea-project/GenAIComps/pull/1246)) (30e3dea) - Fixed tei embedding and tei reranking bug ([#1256](https://github.com/opea-project/GenAIComps/pull/1256)) (fa01f46) - Fixed web-retrievers hub client and tei endpoint issue ([#1270](https://github.com/opea-project/GenAIComps/pull/1270)) (ecb7f7b) - Fixed Dataprep Ingest Data Issue. ([#1271](https://github.com/opea-project/GenAIComps/pull/1271)) (b777db7) - Fixed metric id issue when init multiple Orchestrator instance ([#1280](https://github.com/opea-project/GenAIComps/pull/1280)) (f8e6216) - Bug Fix neo4j dataprep ingest error handling and skip_ingestion argument passing ([#1288](https://github.com/opea-project/GenAIComps/pull/1288)) (4a90692) - Fixed the retriever issue of Milvus ([#1286](https://github.com/opea-project/GenAIComps/pull/1286)) (47f68a4) - Fixed Qdrant retriever RAG issue. ([#1289](https://github.com/opea-project/GenAIComps/pull/1289)) (c3c8497) - Fixed agent message format. ([#1297](https://github.com/opea-project/GenAIComps/pull/1297)) (022d052) - Fixed milvus dataprep ingest files failure ([#1299](https://github.com/opea-project/GenAIComps/pull/1299)) (a033c05) - Fixed docker image security issues ([#1321](https://github.com/opea-project/GenAIComps/pull/1321)) (589587a) - Megaservice / orchestrator metric testing + fixes ([#1348](https://github.com/opea-project/GenAIComps/pull/1348)) (1064b2b) - Fixed finetuning python regex syntax error ([#1446](https://github.com/opea-project/GenAIComps/pull/1446)) (380f95c) - Upgraded Optimum Habana version to fix security check issue ([#1571](https://github.com/opea-project/GenAIComps/pull/1571)) (83350aa) - Make llamaguard compatible with both TGI and vLLM ([#1581](https://github.com/opea-project/GenAIComps/pull/1581)) (4024302) - Documentation - GraphRAG README/compose fixes post refactor ([#1221](https://github.com/opea-project/GenAIComps/pull/1221)) (b38d9f3) - Updated docs for LLamaGuard & WildGuard Microservice ([#1259](https://github.com/opea-project/GenAIComps/pull/1259)) (0df374b) - Fixed Readme errors in dataprep component for all VectorDBs ([#1377](https://github.com/opea-project/GenAIComps/pull/1377)) (492f028) - Refined the README for llms/doc-summarization ([#1437](https://github.com/opea-project/GenAIComps/pull/1437)) (559ebb2) - CI/CD/UT - Refine dataprep test scripts ([#1305](https://github.com/opea-project/GenAIComps/pull/1305)) (a4f6af1)
GenAIEval - Auto Tuner - RAG Pilot - A RAG pipeline tuning tool allowing fine-grained control over key aspects of parsing, chunking, postprocessing, and generating selection, enabling better retrieval and response generation. ([#243](https://github.com/opea-project/GenAIEval/pull/243)) (97da8f2) - Monitoring - Integrate with memory bandwidth exporter to support collection and reporting of memory bandwidth, cpu, mem metrics. ([#218](https://github.com/opea-project/GenAIEval/pull/218)) (df5fd3e) - Add benchmark docker image to support getting metrics among microservices and fixed a missing package for benchmarking with Dockerfile ([#249](https://github.com/opea-project/GenAIEval/pull/249)) (dc3409f) - Metrics - Collect vllm latency metric for e2e test ([#244](https://github.com/opea-project/GenAIEval/pull/244)) (1b6a91d) - Bug Fixes - Fix relative path issue for possion. ([#234](https://github.com/opea-project/GenAIEval/pull/234)) (3b9981a) - Add the missed file in release package ([#233](https://github.com/opea-project/GenAIEval/pull/233)) (28ed0db) - fix the error of TTFT and TPOT while the bench target is chatqna_qlist_pubmed ([#238](https://github.com/opea-project/GenAIEval/pull/238)) (da04a9f) - Fix performance benchmark with pubmed ([#239](https://github.com/opea-project/GenAIEval/pull/239)) (5c8ab6e) - Documentation - Add recommendations to platform optimization documentation (ea086a6)
GenAIInfra - HelmChart - [TDX] Added Intel TDX support to helm charts ([#799](https://github.com/opea-project/GenAIInfra/pull/799)) (040860e) - Add helm starter chart for developing new charts ([#776](https://github.com/opea-project/GenAIInfra/pull/776)) (6154b6c) - HPA enabling usability improvement ([#770](https://github.com/opea-project/GenAIInfra/pull/770)) (3016f5f) - Helm chart for Ollama ([#774](https://github.com/opea-project/GenAIInfra/pull/774)) (7d66afb) - Helm: Added Qdrant support ([#796](https://github.com/opea-project/GenAIInfra/pull/796)) (99ccf0c) - Chatqna: Added Qdrant DB support ([#813](https://github.com/opea-project/GenAIInfra/pull/813)) (5576cfd) - Helm installed application metric Grafana dashboards ([#800](https://github.com/opea-project/GenAIInfra/pull/800)) (f46e8c1) - LLM TextGen Bedrock Support ([#811](https://github.com/opea-project/GenAIInfra/pull/811)) (da37b9f) - codegen: Add rag pipeline and change default UI ([#985](https://github.com/opea-project/GenAIInfra/pull/985)) (46b1b6b) - dataprep/retriever: Support airgap offline environment ([#980](https://github.com/opea-project/GenAIInfra/pull/980)) (b9b10e9) - CSP - Added automated provisioning of CosmosDB and App Insights for OPEA applications ([#657](https://github.com/opea-project/GenAIInfra/pull/657)) (d29bd2d) - Bug Fixes - Fixed the helm chart release dependency update ([#842](https://github.com/opea-project/GenAIInfra/pull/842)) (f121edd) - CI/CD/UT - CI: Enabled milvus related test ([#767](https://github.com/opea-project/GenAIInfra/pull/767)) (5b2cca9)
GenAIStudio - Updated studio fe table UI and updated studio be according to the dataprep refactor ([#32](https://github.com/opea-project/GenAIStudio/pull/32)) (1168507) - [Feat] Added GenAI Studio UI improvement ([#48](https://github.com/opea-project/GenAIStudio/pull/48)) (ad64f7c) - Enabled LLM Traces for sandbox ([#51](https://github.com/opea-project/GenAIStudio/pull/51)) (df6b73e) - Migrated to internal k8 mysql and enable deployment package generation for agentqna ([#52](https://github.com/opea-project/GenAIStudio/pull/52)) (0cddbe0)
## Deprecations ### Deprecated Examples The following GenAI examples are deprecated, and were removed since OPEA v1.3: | Example | Migration Solution | Reasons for Deprecation | |--|--|--| |[FaqGen](https://github.com/opea-project/GenAIExamples/tree/v1.2/FaqGen)|Use the example [ChatQnA](https://github.com/opea-project/GenAIExamples/tree/v1.3/ChatQnA) instead.| Provide users with a unified chatbot experience and reduce redundancy. | ### Deprecated Docker Images The following Docker images are deprecated, and not updated / tagged for OPEA v1.3 release: | Deprecated Docker Image | Migration Solution | Reasons for Deprecation | |--|--|--| |[opea/agent-ui](https://hub.docker.com/r/opea/agent-ui)|Use [opea/agent-openwebui](https://hub.docker.com/r/opea/agent-openwebui) instead.|Open WebUI based UI for better user experience.| |[opea/chathistory-mongo-server](https://hub.docker.com/r/opea/chathistory-mongo-server)|Use [opea/chathistory-mongo](https://hub.docker.com/r/opea/chathistory-mongo) instead.| Follow the OPEA naming rules | |[opea/faqgen](https://hub.docker.com/r/opea/faqgen)|Use [opea/chatqna](https://hub.docker.com/r/opea/chatqna) or [opea/chatqna-without-rerank](https://hub.docker.com/r/opea/chatqna-without-rerank) instead.| FaqGen is deprecated. | |[opea/faqgen-ui](https://hub.docker.com/r/opea/faqgen-ui)|Use [opea/chatqna-ui](https://hub.docker.com/r/opea/chatqna-ui) instead.| FaqGen is deprecated. | |[opea/faqgen-react-ui](https://hub.docker.com/r/opea/faqgen-react-ui)|Use [opea/chatqna-ui](https://hub.docker.com/r/opea/chatqna-ui) instead.| FaqGen is deprecated. | |[opea/feedbackmanagement](https://hub.docker.com/r/opea/feedbackmanagement)|Use [opea/feedbackmanagement-mongo](https://hub.docker.com/r/opea/feedbackmanagement-mongo) instead.| Follow the OPEA naming rules | |[opea/promptregistry-mongo-server](https://hub.docker.com/r/opea/promptregistry-mongo-server)|Use [opea/promptregistry-mongo](https://hub.docker.com/r/opea/promptregistry-mongo) instead.| Follow the OPEA naming rules | The following Docker images are deprecated, and will not be updated / tagged since OPEA v1.4 release: | Deprecated Docker Image | Migration Solution | Reasons for Deprecation | |--|--|--| |[opea/chathistory-mongo](https://hub.docker.com/r/opea/chathistory-mongo)|Use [opea/chathistory](https://hub.docker.com/r/opea/chathistory) instead. The Docker image will be released with the `latest` tag before the v1.4 release. | OPEA introduced OPEAStore to decouple chathistory component from MongoDB. | |[opea/feedbackmanagement-mongo](https://hub.docker.com/r/opea/feedbackmanagement-mongo)|Use [opea/feedbackmanagement](https://hub.docker.com/r/opea/feedbackmanagement) instead. The Docker image will be released with the `latest` tag before the v1.4 release.| OPEA introduced OPEAStore to decouple feedback management component from MongoDB. | |[opea/promptregistry-mongo](https://hub.docker.com/r/opea/promptregistry-mongo)|Use [opea/promptregistry](https://hub.docker.com/r/opea/promptregistry) instead. The Docker image will be released with the `latest` tag before the v1.4 release.| OPEA introduced OPEAStore to decouple prompt registry component from MongoDB. | [All OPEA docker images](https://github.com/opea-project/GenAIExamples/blob/v1.3/docker_images_list.md) ### Deprecated GenAIExample Variables | Example | Type | Variable | Migration Solution | |--|--|--|--| |[ChatQnA](https://github.com/opea-project/GenAIExamples/tree/v1.3/ChatQnA)|environment variable|`your_hf_api_token`|Removed from Intel AIPC deployment. Use the environment variable `HUGGINGFACEHUB_API_TOKEN` instead. This change aligns with the standardized naming conventions for environment variables.| |[ChatQnA](https://github.com/opea-project/GenAIExamples/tree/v1.3/ChatQnA)|environment variable|`OLLAMA_HOST`|Removed from Intel AIPC deployment. Instead, users can customize `LLM_SERVER_HOST_IP` in `ChatQnA/docker_compose/intel/cpu/aipc/compose.yaml`.| |[DocIndexRetriever](https://github.com/opea-project/GenAIExamples/tree/v1.3/DocIndexRetriever)|environment variable|`TGI_LLM_ENDPOINT`|Removed due to no uses.| |[DocIndexRetriever](https://github.com/opea-project/GenAIExamples/tree/v1.3/DocIndexRetriever)|environment variable|`MEGA_SERVICE_HOST_IP`|Removed due to no uses.| |[DocIndexRetriever](https://github.com/opea-project/GenAIExamples/tree/v1.3/DocIndexRetriever)|environment variable|`LLM_SERVICE_HOST_IP`|Removed due to no uses.| |[GraphRAG](https://github.com/opea-project/GenAIExamples/tree/v1.3/GraphRAG)|environment variable|`MAX_OUTPUT_TOKENS`|Instead, it has been split into two new environment variables: `MAX_INPUT_TOKENS` (default: 4096) and `MAX_TOTAL_TOKENS` (default: 8192) to control the maximum token limits.| ### Deprecated GenAIComps Parameters | Component | Parameter | Migration Solution | |--|--|--| |[agent](https://github.com/opea-project/GenAIComps/tree/v1.3/comps/agent)|`with_store` of `agent_config` in the Assistants APIs|Its functionality is now fully covered by the new `memory_type` parameter. In v1.3, please use `"with_memory": true` and `"memory_type": persistent` as its replacement. The `with_memory` parameter in `agent_config` of APIs is now enabled by default (true) for enabling multi-turn conversations. Please refer to the [guide](https://github.com/opea-project/GenAIComps/blob/v1.3/comps/agent/src/README.md#agent-memory) for more details.| ## Updated Dependencies | Dependency | Hardware | Scope | Version | Version in OPEA v1.2 | Comments | |--|--|--|--|--|--| |gradio|-|all examples|5.11.0|5.5.0|| |huggingface/text-generation-inference|AMD GPU|all examples|2.4.1-rocm|2.3.1-rocm|| |huggingface/text-embeddings-inference|all|all examples|cpu-1.6|cpu-1.5|| |langchain
langchain_community|-|llms/doc-summarization
llms/faq-generation|0.3.14|0.3.15|Avoid bugs in FaqGen and DocSum.| |optimum-habana|Gaudi|lvms/llama-vision|1.17.0|-|| |pytorch|Gaudi|all components|2.5.1|2.4.0|| |transformers|-|lvms/llama-vision|4.48.0|4.45.1|| |vllm|Xeon|all supported examples except EdgeCraftRAG|v0.8.3|-|| |vllm|Gaudi|all supported examples except EdgeCraftRAG|v0.6.6.post1+Gaudi-1.20.0|v0.6.4.post2+Gaudi-1.19.0|| |vllm|AMD GPU|all supported examples|rocm6.3.1_instinct_vllm0.8.3_20250410|-|| ## Changes to Default Behavior - [[agent](https://github.com/opea-project/GenAIComps/tree/v1.3/comps/agent)] The default model changed from `meta-llama/Meta-Llama-3-8B-Instruct` to `meta-llama/Llama-3.3-70B-Instruct`. ## Validated Hardware - Intel® Arc™ Graphics GPU (A770) - Intel® Gaudi® Al Accelerators (2nd, 3rd) - Intel® Xeon® Scalable processor (4th, 5th, 6th) - AMD® Instinct™ MI300X Accelerators (CDNA3) ## Validated Software - AMD® ROCm™ Software [v6.3.3](https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.3.2/install/quick-start.html) - Docker 28.0.4 - Docker Compose v2.34.0 - Intel® Gaudi® software and drivers [v1.20](https://docs.habana.ai/en/v1.20.0/Installation_Guide/index.html) - Kubernetes v1.29.15 - TEI v1.6 - TGI v2.4.0 (Xeon), v2.3.1(Gaudi), v2.4.1 (ROCm) - Torch v2.5.1 - Ubuntu 22.04 - vLLM v0.8.3 (Xeon/ROCm), v0.6.6 (Gaudi) ## Known Issues - [AvatarChatbot](https://github.com/opea-project/GenAIExamples/tree/v1.3/AvatarChatbot) can not work in K8s environment because of a functional gap in wav2clip service. ([GenAIExamples#](https://github.com/opea-project/GenAIExamples/pull/1506)) ## Full Changelogs - GenAIExamples: [v1.2...v1.3](https://github.com/opea-project/GenAIExamples/compare/v1.2...v1.3) - GenAIComps: [v1.2...v1.3](https://github.com/opea-project/GenAIComps/compare/v1.2...v1.3) - GenAIInfra: [v1.2...v1.3](https://github.com/opea-project/GenAIInfra/compare/v1.2...v1.3) - GenAIEval: [v1.2...v1.3](https://github.com/opea-project/GenAIEval/compare/v1.2...v1.3) - GenAIStudio: [v1.2...v1.3](https://github.com/opea-project/GenAIStudio/compare/v1.2...v1.3) - docs: [v1.2...v1.3](https://github.com/opea-project/docs/compare/v1.2...v1.3) ## Contributors This release would not have been possible without the contributions of the following organizations and individuals. ### Contributing Organizations - `Amazon`: Ollama deployment, Bedrock integration, OVMS integration and bug fixes. - `AMD`: vLLM enablement on AMD GPUs for key examples, AMD GPUs enabling on more examples, AMD OPEA blogs. - `ArangoDB`: OPEA Store and ArangoDB integration. - `Intel`: Development and improvements to GenAI examples, components, infrastructure, and evaluation. - `Infosys`: Azure support and documentation updates. - `National Chiao Tung University`: Documentation updates. - `Prediction Guard`: Maintenance of Prediction Guard components. ### Individual Contributors For a comprehensive list of individual contributors, please refer to the [Full Changelogs](#full-changelogs) section.