# OPEA 2024 - 2025 Roadmap

## May 2024

### Contribution

- **Components**
  - ASR
  - Data Prep
  - Embedding
  - Guardrails
  - LLM (Gaudi TGI)
  - Rerank
  - Retrieval
  - TTS
  - VectorDB

- **Use Cases/Examples**
  - ChatQnA
  - CodeGen
  - CodeTrans

- **Cloud Native**
  - OneClick OPEA on ChatQnA
  - OneClick OPEA on CodeGen
  - GenAI microservice connector

- **Evaluation & Others**
  - CICD & Validation
  - Eval: E2E (GenAIComps & GenAIExamples), lm-eval-harness, bigcode-eval-harness
  - RAGAS evaluation service

### AI Models

- LLM: llama2 (7b, 13b, 70b), llama3 (8b, 70b), code-llama, Llama guard
- Embedding: BGE-base

### AI Tools Integration

- VectorDB: Chroma
- Framework: Langchain

### Deployment Type

- On Prem,IDC (Xeon, Gaudi)

## June 2024

### Contribution

- **Components**
  - LLM (Xeon vLLM & Ray, Ollama)
  - OVMS
  - prompting
  - user feedback management
  - Mega Component (MI6 RAG service)

- **Use Cases/Examples**
  - DocSum
  - SearchQnA

- **Cloud Native**
  - OneClick OPEA for 2 more examples
  - GMC with switch support (dynamic pipelines)
  - Helm charts/templates for custom yamls (refactoring)

- **Evaluation & Others**
  - CICD & Validation
  - Eval: E2E (GenAIComps & GenAIExamples) Gaudi (2) and CPUs in CICD cluster

### AI Models

- LLM: mistral-7B, mixtral-8x7B
- Embedding: E5-mistral-7b-instruct, all-mpnet-base-v2

### AI Tools Integration

- VectorDB: Pinecone, Redis
- Framework: Llamaindex, Haystack

### Deployment Type

- On Prem,IDC (Xeon, Gaudi)

## July 2024

### Contribution

- **Components**
  - LVM (Gaudi vLLM & Ray)
  - vectordb (svs)
  - Gateway guardrail, Auth Z/N

- **Use Cases/Examples**
  - FAQGen

- **Cloud Native**
  - OpenShift enablement for OPEA
  - OneClick OPEA for 3 more examples
  - Security (Service Mesh, guardrails)

- **Evaluation & Others**
  - CICD & Validation
  - Eval: E2E (GenAIComps & GenAIExamples)

### AI Models

- LLM: Phi, Gemma
- Embedding: all-MiniLM-L6-v2, paraphrase-albert-small-v2

### AI Tools Integration

- VectorDB: PGVector, Qdrant

### Deployment Type

## Aug 2024

### Contribution

- **Components**
  - Documentation
  - Test automation script
  - Telemetry

- **Use Cases/Examples**
  - Documentation
  - Test automation script

- **Cloud Native**
  - Demo K8s resource management
  - Documentation on autoscaler analysis

- **Evaluation & Others**
  - CICD & Validation
  - Eval: E2E (GenAIComps & GenAIExamples)

### AI Models

- Vision: llava
- Mixtral-8x22B

### AI Tools Integration

- VectorDB: Milvus

### Deployment Type

- Public Cloud AWS (Xeon CPU & NV GPU)

## Sep 2024

### Contribution

- **Components**
  - Microservice for Image and Video

- **Use Cases/Examples**
  - Text to Image generation
  - Image to Video generation
  - Playground (composable and configurable)

- **Cloud Native**

- **Evaluation & Others**
  - CICD & Validation
  - Eval: E2E (GenAIComps & GenAIExamples)

### AI Models

- Diffusion model:
  - Stable Diffusion XL
  - Stable Diffusion 3M
  - Stable Video Diffusion

### AI Tools Integration

- VectorDB: Weaviate

### Deployment Type

## Q4 2024

### Contribution

- **Components**
  - Fine-tuning E2E pipeline
  - Knowledge Graph

- **Use Cases/Examples**
  - Fine-tuning (Lora)
  - AI Agent (single Agent with text and Audio as user interface)
  - Closed source LLM
  - GraphRAG

- **Cloud Native**
  - Static tuning on Resource management for deployment

- **Evaluation & Others**
  - CICD & Validation
  - Eval: E2E (GenAIComps & GenAIExamples)

### AI Models

- LLM open: Grok 1
- LLM Close: GPT3.5/4/4o, Claude 3/3.5
- AWS Bedrock endpoint

### AI Tools Integration

- Knowledge graph: Neo4j
- Agent: LangGraph

### Deployment Type

- Public Cloud (Azure, GCP, Oracle, AWS)
- AI PC (Intel)

# OPEA 2025 Roadmap 
## Release Cadence
- Release cycles extended from **2 months to 3 months** (TSC approved)
- Upcoming versions:  

| Version | Release Date | Key Features |
|---------|--------------|--------------|
| v1.6    | Jan 2026     | Domain-specific AI Agent Blueprints with Partners, Leading open source LLM, Image and Video Diffusion models |
| v1.5    | Oct 2025     | RouteLLM, Finetuning (Advanced), Next Agent Example |
| v1.4    | Jul 2025     | Agent (human in the loop), Finance Agent Advanced, GraphRAG (Arango DB), AI Resource Optimizer |
| v1.3    | Apr 2025     | Agent (multi-turn message), Advanced AgentQnA, Finance Agent Basic, DocSum (Performance, accuracy and stability)  |
| v1.2    | Jan 2025     | vLLM Arc GPU via OpenVINO, Langchain Integration, Llamaindex Integration, Eval Benchmark for ChatQnA  |


## Q1 2025 (v1.2 release)

### Contribution

- **GenAI Component**
  - vLLM Arc GPU via OpenVINO
  - Opensearch vector DB
  - Elastic search
  - POC for Model context protocol

- **GenAI Examples**
  - Langchain Integration
  - Llamaindex Integration

- **GenAI Infra**
  - OPEA on k8s guide
  - HPA support in GMC
  - Istio m/TLS integration

- **GenAIEval**
  - Eval benchmark for China ecosystem
  - K8s conformance test
  - Long context benchmark enhancement
  - ChatQnA Benchmark (performance, accuracy and stability)

### AI Models

- BAAI/bge-base-zh-v1.5
- AWS bedrock endpoint

## Q2 2025  (v1.3 release)

### Contribution

- **GenAI Component**
  - Agent (multi-turn message)

- **GenAI Examples**
  - Advanced AgentQnA
  - Finance Agent Basic
  - vLLM enablement for GenAI examples
  - *Haystack Integration

- **GenAI Infra**
  - Enhance existing HELM charts (8 GenAI Examples)
  - OIM basic (container structure)
  - HPA Scaling for IAAS

- **GenAIEval**
  - Initial DocuSum Benchmark Support (Performance, accuracy and stability)
  - Long context benchmark enhancement (vLLM-Gaudi)

### AI Models

- Deepseek v3, R1, 6 distilled LLM
- Mistral (Large, Small)
- Granite (IBM)

## Q3 2025 (v1.4 release)

### Contribution

- **GenAI Component**
  - Agent (human in the loop)

- **GenAI Examples**
  - Finance Agent Advanced
  - GraphRAG (Arango DB)
  - Finetuning (Basic)
  - Model Context Protocol

- **GenAI Infra**
  - OIM enhancement
  - AI Resource Optimizer

- **GenAIEval**
  - AI Agent (performance, accuracy and stability)

### AI Models

- Deepseek upgrades
- Llama4
- Falcon LLM
- Falcon LVM
- Finetuned Financial model
    
## Q4 2025 (v1.5 release)  

### Contribution

- **GenAI Component**
  - RouteLLM

- **GenAI Examples**
  - Finetuning (Advanced)
  - Next Agent Example

- **GenAI Infra**
  - OIM advanced

- **GenAIEval**
  - More GenAI Example performance, accuracy and stability (continuous)

### AI Models

- Next advanced LLMs

## Q1 2026 (v1.6 release)

### Contribution

- **GenAI Examples**
  - Domain specific AI Agent Blueprint backed by customers/partners
  - Leading open source LLM (reasoning model, FM)
  - Image, Video Diffusion model