Commit Graph

12 Commits

Author SHA1 Message Date
Ubuntu 6e4e5c40dd chore: resolve .env.example merge conflict; keep feat/pluggable-graph-backend version
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-25 21:11:06 +00:00
Ubuntu ba9c8d1f42 feat(ontology): make entity/edge type limits configurable via env vars
Revert default limits back to 10 edges and 12 entities (10 specific + 2
fallback), matching Zep Cloud's maximum. Expose ONTOLOGY_MAX_ENTITY_TYPES
and ONTOLOGY_MAX_EDGE_TYPES in Config so operators can override without
touching code. Prompts now inject the live values at request time.
Also replace Chinese comments in .env.example with English equivalents.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-25 19:56:44 +00:00
Ubuntu 0ce4d6c10e docs(env): update Gemini example model to gemini-3.1-flash-lite-preview
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-25 19:25:19 +00:00
Ubuntu 3e270f2e16 docs: document graphiti+neo4j backend architecture and translate .env.example to English
- INSTALL.md: add section 3 covering the pluggable graph backend
  (architecture diagram, interface table, Zep vs Graphiti comparison,
  optional deps, env vars, Azure ACI deployment details, test instructions)
- .env.example: translate all Chinese comments to English; add
  GRAPH_BACKEND selector and Graphiti/Neo4j variables (commented out)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-25 15:32:18 +00:00
Ubuntu d2ee1d3d5f docs(env): document GRAPH_BACKEND, Neo4j, and Gemini configuration
Add commented sections for the new pluggable graph backend and Gemini
LLM provider options so users know what variables are available.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-25 13:13:27 +00:00
Ubuntu b5c4d4a336 feat(auth): add JWT login screen, production Dockerfile and Azure Container App Bicep
- Backend: POST /api/auth/login endpoint (PyJWT HS256, 24h expiry)
  require_auth before_request middleware protecting all /api/* routes
  except /login and /health; wsgi.py entry point for gunicorn;
  Flask serves compiled Vue SPA in production
- Frontend: LoginView.vue (MiroFish dark aesthetic), auth.js reactive
  store, Axios Bearer token injection + 401 → /login redirect,
  Vue Router global guard protecting all routes
- i18n: login keys added to en/zh/es/ca locale files
- Dockerfile: multi-stage build (node:20-slim → python:3.11-slim +
  gunicorn), single port 5001
- Azure: container-app.bicep following CTTI guidelines — Log Analytics
  (NOR0016-C 90d retention), Container Apps Environment, all .env vars
  as env vars (secrets via secretRef, plain values inline)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-24 18:46:39 +00:00
666ghj 9556854fbf refactor(.env.example): update LLM API configuration comments for clarity and add usage note 2026-01-20 18:05:36 +08:00
666ghj ca24ee09d1 chore(env.example): update LLM model configuration and clarify boost settings. 2026-01-15 23:11:26 +08:00
666ghj a47eb1eaef Refactor project structure by removing Docker support and updating environment configuration
- Deleted docker-compose.yml, backend Dockerfile, frontend Dockerfile, and nginx configuration to streamline project setup.
- Updated .env.example to reorganize LLM and ZEP API configurations for clarity and ease of use.
- Enhanced README.md to reflect changes in project structure and provide clearer setup instructions.
2025-12-19 13:58:35 +08:00
666ghj e432e223df Update project configuration and structure with Docker support and environment variable adjustments
- Updated .env.example to reflect new LLM configuration with Aliyun's API.
- Enhanced .gitignore to include additional files and directories for better exclusion of sensitive and build artifacts.
- Added docker-compose.yml for streamlined deployment of backend and frontend services.
- Introduced Dockerfiles for both backend and frontend to facilitate containerized builds.
- Created README.md to provide comprehensive project documentation and setup instructions.
- Established nginx configuration for frontend to support API proxying and static file serving.
2025-12-17 18:17:40 +08:00
666ghj 39253b3213 Update .env.example and enhance create_model function for dual LLM configuration
- Updated .env.example to include new keys for dual LLM configuration, allowing for both general and boost settings.
- Modified create_model function to support an optional use_boost parameter, enabling the selection of either general or boost LLM configurations based on availability.
- Improved logging to indicate which LLM configuration is being used during model creation, enhancing clarity for users.
2025-12-04 15:51:25 +08:00
666ghj 08f417f3b7 Introduce Project ID for context management, finalizing the stateful API pipeline from file submission to graph construction. 2025-11-28 17:21:08 +08:00