AIRegulation/AIRegulation-DocAnalysis
7
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
main-ruqi
AIRegulation-DocAnalysis/.env.example

144 lines
4.7 KiB
Plaintext
Raw Permalink Normal View History

first commit
2026-04-28 11:29:33 +08:00
# .env.example - 环境变量配置示例
update
2026-05-14 15:07:34 +08:00
# AI+合规智能中枢
first commit
2026-04-28 11:29:33 +08:00
update
2026-05-14 15:07:34 +08:00
# ===== 应用基础配置 =====
APP_NAME=AI+合规智能中枢
APP_VERSION=0.1.0
DEBUG=false
# ===== Milvus向量数据库配置 =====
fix 文档管理模块 & 法规对话模块
2026-05-20 23:34:08 +08:00
MILVUS_HOST=6.86.80.8
first commit
2026-04-28 11:29:33 +08:00
MILVUS_PORT=19530
Refactor document handling and update Milvus collection settings - Removed multiple failed document entries from `documents.json`. - Added a new document entry with updated metadata and changed the index name to `regulations_dense_1024_v2`. - Updated architecture documentation to reflect changes in the Milvus collection name. - Adjusted requirements by removing the sqlalchemy dependency. - Modified test cases to align with new document structure and naming conventions. - Introduced a new test file for Milvus vector index runtime recovery and error handling. - Updated assertions in various test files to ensure compatibility with the new schema.
2026-05-26 20:21:31 +08:00
MILVUS_COLLECTION=regulations_dense_1024_v2
update
2026-05-14 15:07:34 +08:00
MILVUS_DB_NAME=default
fix 文档管理模块 & 法规对话模块
2026-05-20 23:34:08 +08:00
MILVUS_INDEX_TYPE=IVF_FLAT
MILVUS_NLIST=128
MILVUS_NPROBE=16
first commit
2026-04-28 11:29:33 +08:00
update
2026-05-14 15:07:34 +08:00
# ===== 嵌入模型配置 =====
Fix SSE route dependency and align architecture docs
2026-05-18 16:32:42 +08:00
EMBEDDING_MODEL=text-embedding-v3
feat: Migrate document parsing to Aliyun and update embedding configurations - Updated LocalDocumentParser to include raw_layouts and artifact_prefix from settings. - Added new documents with failure reasons and metadata to documents.json for better error tracking. - Created a new documentation file detailing the Aliyun ingest implementation process. - Updated RFC to reflect changes in the parsing backend and embedding dimensions. - Modified tests to accommodate the new embedding dimension of 1024 and updated parser and chunk builder assertions. - Verified migration configurations to ensure correct settings for embedding model and backend.
2026-05-18 22:30:28 +08:00
EMBEDDING_DIM=1024
Fix SSE route dependency and align architecture docs
2026-05-18 16:32:42 +08:00
EMBEDDING_API_KEY=your_embedding_api_key_here
EMBEDDING_BASE_URL=http://6.86.80.4:30080/v1
EMBEDDING_TIMEOUT_SECONDS=120
first commit
2026-04-28 11:29:33 +08:00
update
2026-05-14 15:07:34 +08:00
# ===== MinIO对象存储配置 =====
fix 文档管理模块 & 法规对话模块
2026-05-20 23:34:08 +08:00
MINIO_ENDPOINT=6.86.80.8:9000
first commit
2026-04-28 11:29:33 +08:00
MINIO_ACCESS_KEY=minioadmin
MINIO_SECRET_KEY=minioadmin123
MINIO_BUCKET=compliance-docs
update
2026-05-14 15:07:34 +08:00
MINIO_SECURE=false
first commit
2026-04-28 11:29:33 +08:00
update
2026-05-14 15:07:34 +08:00
# ===== Redis配置 =====
fix 文档管理模块 & 法规对话模块
2026-05-20 23:34:08 +08:00
REDIS_HOST=6.86.80.8
first commit
2026-04-28 11:29:33 +08:00
REDIS_PORT=6379
update
2026-05-14 15:07:34 +08:00
REDIS_PASSWORD=
REDIS_DB=0
first commit
2026-04-28 11:29:33 +08:00
update
2026-05-14 15:07:34 +08:00
# ===== PostgreSQL配置 =====
fix 文档管理模块 & 法规对话模块
2026-05-20 23:34:08 +08:00
POSTGRES_HOST=6.86.80.8
first commit
2026-04-28 11:29:33 +08:00
POSTGRES_PORT=5432
POSTGRES_USER=compliance
POSTGRES_PASSWORD=compliance123
POSTGRES_DB=compliance_db
update
2026-05-14 15:07:34 +08:00
# ===== 文档处理配置 =====
first commit
2026-04-28 11:29:33 +08:00
CHUNK_SIZE=512
update
2026-05-14 15:07:34 +08:00
CHUNK_OVERLAP=50
MAX_FILE_SIZE_MB=100
Fix SSE route dependency and align architecture docs
2026-05-18 16:32:42 +08:00
DOCUMENT_METADATA_PATH=backend/data/documents.json
feat: Migrate document parsing to Aliyun and update embedding configurations - Updated LocalDocumentParser to include raw_layouts and artifact_prefix from settings. - Added new documents with failure reasons and metadata to documents.json for better error tracking. - Created a new documentation file detailing the Aliyun ingest implementation process. - Updated RFC to reflect changes in the parsing backend and embedding dimensions. - Modified tests to accommodate the new embedding dimension of 1024 and updated parser and chunk builder assertions. - Verified migration configurations to ensure correct settings for embedding model and backend.
2026-05-18 22:30:28 +08:00
PARSER_BACKEND=aliyun
CHUNK_BACKEND=aliyun
update for 1. 优化 2.中英切换
2026-06-10 11:10:36 +08:00
# 文档元数据存储后端：json（默认，无需数据库）或 postgres（启用 PG 持久化）
# ⚠ 以下功能需要 postgres（设为 json 时功能静默降级或报 500）：
# - Direction B: 合规分析历史记录 (/compliance/history/*)
# - Direction B: DOCX 报告下载
# - Direction C: Finding Chat 消息持久化
fix 文档管理模块 & 法规对话模块
2026-05-20 23:34:08 +08:00
DOCUMENT_REPOSITORY_BACKEND=json
1. Add 登陆功能 2. 调整字体大小 3. 新增部分功能
2026-06-05 18:00:31 +08:00
# Set to true only when a Celery worker is running (./dev.sh start worker).
# Default false: document processing runs in FastAPI's threadpool (no external worker needed).
USE_CELERY_WORKER=false
Fix SSE route dependency and align architecture docs
2026-05-18 16:32:42 +08:00
fix somethings
2026-06-08 11:16:28 +08:00
# ===== 法规感知爬取配置 =====
PERCEPTION_CRAWL_TIMEOUT_SECONDS=120
PERCEPTION_MAX_EVENTS_PER_SOURCE=100
PERCEPTION_DIFF_SIMILARITY_THRESHOLD=0.85
Fix SSE route dependency and align architecture docs
2026-05-18 16:32:42 +08:00
# ===== 阿里云文档解析 =====
ALIBABA_ACCESS_KEY_ID=your_aliyun_access_key_id
ALIBABA_ACCESS_KEY_SECRET=your_aliyun_access_key_secret
ALIBABA_ENDPOINT=docmind-api.cn-hangzhou.aliyuncs.com
feat: Migrate document parsing to Aliyun and update embedding configurations - Updated LocalDocumentParser to include raw_layouts and artifact_prefix from settings. - Added new documents with failure reasons and metadata to documents.json for better error tracking. - Created a new documentation file detailing the Aliyun ingest implementation process. - Updated RFC to reflect changes in the parsing backend and embedding dimensions. - Modified tests to accommodate the new embedding dimension of 1024 and updated parser and chunk builder assertions. - Verified migration configurations to ensure correct settings for embedding model and backend.
2026-05-18 22:30:28 +08:00
ALIYUN_PARSE_POLL_INTERVAL_SECONDS=5
ALIYUN_PARSE_TIMEOUT_SECONDS=900
ALIYUN_PARSE_LAYOUT_STEP_SIZE=50
ALIYUN_LLM_ENHANCEMENT=true
ALIYUN_ENHANCEMENT_MODE=VLM
DOCUMENT_PARSE_ARTIFACT_PREFIX=artifacts
PARSER_FAILURE_MODE=fail
update
2026-05-14 15:07:34 +08:00
# ===== API服务配置 =====
API_HOST=0.0.0.0
API_PORT=8000
# ===== LLM配置（必填）=====
# LLM提供商选择: qwen / deepseek / qwen_vl
LLM_PROVIDER=deepseek
LLM_MODEL=deepseek-v4-flash
LLM_MAX_TOKENS=4096
LLM_TEMPERATURE=0.7
# ===== 统一API代理配置 =====
# 使用new-api代理服务，支持多个LLM模型
# 获取API Key: 向管理员申请
QWEN_API_KEY=your_api_key_here
DEEPSEEK_API_KEY=your_api_key_here
QWEN_BASE_URL=http://6.86.80.4:30080/v1
DEEPSEEK_BASE_URL=http://6.86.80.4:30080/v1
# ===== 可用模型 =====
# Qwen系列: qwen3.5-plus, qwen3-plus, qwen-max, qwen-turbo, qwen-long
# Qwen VL系列: qwen3-vl-plus, qwen-vl-max
# DeepSeek系列: deepseek-v4-flash, deepseek-v3.2, deepseek-v3, deepseek-chat, deepseek-coder
feat: Migrate document parsing to Aliyun and update embedding configurations - Updated LocalDocumentParser to include raw_layouts and artifact_prefix from settings. - Added new documents with failure reasons and metadata to documents.json for better error tracking. - Created a new documentation file detailing the Aliyun ingest implementation process. - Updated RFC to reflect changes in the parsing backend and embedding dimensions. - Modified tests to accommodate the new embedding dimension of 1024 and updated parser and chunk builder assertions. - Verified migration configurations to ensure correct settings for embedding model and backend.
2026-05-18 22:30:28 +08:00
QWEN_MODEL=qwen3.6-plus
update
2026-05-14 15:07:34 +08:00
QWEN_VL_MODEL=qwen3-vl-plus
DEEPSEEK_MODEL=deepseek-v4-flash
# ===== RAG配置 =====
RAG_TOP_K=10
fix 文档管理模块 & 法规对话模块
2026-05-20 23:34:08 +08:00
RAG_RETRIEVAL_TOP_K=20
update
2026-05-14 15:07:34 +08:00
RAG_MAX_CONTEXT_TOKENS=4000
RAG_SUMMARY_MAX_TOKENS=1024
1. Add 登陆功能 2. 调整字体大小 3. 新增部分功能
2026-06-05 18:00:31 +08:00
RAG_SKILLS_MAX_TOKENS=2048
Fix SSE route dependency and align architecture docs
2026-05-18 16:32:42 +08:00
1. Add 登陆功能 2. 调整字体大小 3. 新增部分功能
2026-06-05 18:00:31 +08:00
# ── Reranker (Cross-Encoder) ──────────────────────────────────────────────────
# Set RERANKER_ENABLED=true and point to a TEI or Cohere-compatible rerank API.
# Recommended model: BAAI/bge-reranker-v2.5-gemma2-lightweight (lighter) or
# BAAI/bge-reranker-v2-m3 (heavier, higher quality).
# The endpoint must expose POST /rerank (TEI style) or POST /v1/rerank (Cohere style).
RERANKER_ENABLED=true
RERANKER_BASE_URL=http://6.86.80.4:30080/v1
fix 文档管理模块 & 法规对话模块
2026-05-20 23:34:08 +08:00
RERANKER_MODEL=BAAI/bge-reranker-v2-m3
RERANKER_API_KEY=
RERANKER_TOP_K=5
Fix SSE route dependency and align architecture docs
2026-05-18 16:32:42 +08:00
# ===== 会话配置 =====
SESSION_MAX_SESSIONS=100
SESSION_TIMEOUT_MINUTES=30
1. Add 登陆功能 2. 调整字体大小 3. 新增部分功能
2026-06-05 18:00:31 +08:00
# SESSION_BACKEND=redis 启用 Redis 持久化会话（需要 Redis 可用，推荐生产环境）
# SESSION_BACKEND=memory 使用内存会话（重启丢失，适合本地开发）
SESSION_BACKEND=memory
# ===== 认证配置 (Auth) =====
# 生产环境必须替换为强随机密钥:
# python -c "import secrets; print(secrets.token_hex(32))"
AUTH_SECRET_KEY=change-me-in-production-must-be-32-or-more-characters-long
AUTH_ALGORITHM=HS256
# Token 有效期（分钟），默认 8 小时
AUTH_TOKEN_EXPIRE_MINUTES=480
# 设为 false 可跳过认证（仅限本地开发调试，生产必须 true）
AUTH_ENABLED=true
# ===== CORS =====
# 逗号分隔的允许跨域来源列表，生产环境绝不能使用 *
CORS_ALLOW_ORIGINS=http://localhost:5173
Reference in New Issue Copy Permalink