Deployment updates #96
Conversation
…odule into streaming-feature-opensearch
… streaming-feature-opensearch
Get update from wip into streaming-feature-opensearch
… streaming-feature-opensearch
… streaming-feature-opensearch
…tcodelabs/RAG-Module into rag-deployment-ec2
… for enhanced functionality
…rom docker-compose
RAG System Security Assessment ReportRed Team Testing with DeepTeam Framework Executive SummarySystem Security Status: VULNERABLE Overall Pass Rate: 0.0% Risk Level: HIGH Attack Vector Analysis
Only tested attack categories are shown above. Vulnerability Assessment
Multilingual Security Analysis
Failed Security Tests Analysis
(2 additional failures not shown) Security RecommendationsPriority Actions RequiredCritical Vulnerabilities (Immediate Action Required):
Attack Vector Improvements:
Specific Technical Recommendations:
General Security Enhancements:
Testing MethodologyThis security assessment used DeepTeam, an advanced AI red teaming framework that simulates real-world adversarial attacks. Test Execution Process
Attack Categories TestedSingle-Turn Attacks:
Multi-Turn Attacks:
Vulnerabilities Assessed
Language SupportTests were conducted across multiple languages:
Pass/Fail Criteria
Report generated on 2025-12-16 06:14:38 by DeepTeam automated red teaming pipeline |
RAG System Evaluation ReportDeepEval Test Results Summary
Total Tests: 20 | Passed: 0 | Failed: 20 Detailed Test Results| Test | Language | Category | CP | CR | CRel | AR | Faith | Status | Legend: CP = Contextual Precision, CR = Contextual Recall, CRel = Contextual Relevancy, AR = Answer Relevancy, Faith = Faithfulness Failed Test Analysis
(90 additional failures not shown) RecommendationsContextual Precision (Score: 0.000): Consider improving your reranking model or adjusting reranking parameters to better prioritize relevant documents. Contextual Recall (Score: 0.000): Review your embedding model choice and vector search parameters. Consider domain-specific embeddings. Contextual Relevancy (Score: 0.000): Optimize chunk size and top-K retrieval parameters to reduce noise in retrieved contexts. Answer Relevancy (Score: 0.000): Review your prompt template and LLM parameters to improve response relevance to the input query. Faithfulness (Score: 0.000): Strengthen hallucination detection and ensure the LLM stays grounded in the provided context. Report generated on 2025-12-16 06:14:51 by DeepEval automated testing pipeline |
This pull request introduces a new notification server for SSE-based LLM orchestration streaming, integrates it into the Docker Compose stack, and makes several configuration and networking adjustments. The most significant changes are the addition of the
notification-serverservice, the introduction of theopensearch-nodeservice, and updates to network exposure for several services. Below are the most important changes grouped by theme:New Notification Server Implementation:
Added a new
notification-serverservice, including its full Node.js/Express implementation (notification-server/directory:Dockerfile,package.json,.gitignore,index.js,src/server.js,src/config.js,src/connectionManager.js,src/openSearch.js,src/sseUtil.js,src/streamQueue.js). This server provides SSE endpoints for streaming LLM orchestration responses, manages client connections, queues requests, and integrates with the orchestration API. [1] [2] [3] [4] [5] [6] [7] [8] [9] [10]Added the
notification-serverservice todocker-compose.ymlwith appropriate environment variables, dependencies, volumes, and network configuration.OpenSearch Integration:
opensearch-nodeservice todocker-compose.ymlfor search and analytics, including its configuration, environment variables, volumes, and network setup. [1] [2]Networking and Port Exposure Changes:
Updated several service port mappings in
docker-compose.ymlto expose ports on all interfaces instead of only on127.0.0.1(localhost), affectinglangfuse-worker,clickhouse,minio, andredisservices. This change allows external access to these services from outside the host machine. [1] [2] [3] [4]Updated the Vite dev server configuration (
GUI/vite.config.ts) to explicitly allow connections from specific hosts, including the production domain and localhost.Minor Code Cleanups: