c22b03dc07
- 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.
97 lines
2.5 KiB
Plaintext
97 lines
2.5 KiB
Plaintext
# .env.example - 环境变量配置示例
|
||
# AI+合规智能中枢
|
||
|
||
# ===== 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 =====
|
||
MILVUS_HOST=localhost
|
||
MILVUS_PORT=19530
|
||
MILVUS_COLLECTION=regulations_dense_1024_v1
|
||
MILVUS_DB_NAME=default
|
||
|
||
# ===== 嵌入模型配置 =====
|
||
EMBEDDING_MODEL=text-embedding-v3
|
||
EMBEDDING_DIM=1024
|
||
EMBEDDING_API_KEY=your_embedding_api_key_here
|
||
EMBEDDING_BASE_URL=http://6.86.80.4:30080/v1
|
||
EMBEDDING_TIMEOUT_SECONDS=120
|
||
|
||
# ===== MinIO对象存储配置 =====
|
||
MINIO_ENDPOINT=localhost:9000
|
||
MINIO_ACCESS_KEY=minioadmin
|
||
MINIO_SECRET_KEY=minioadmin123
|
||
MINIO_BUCKET=compliance-docs
|
||
MINIO_SECURE=false
|
||
|
||
# ===== Redis配置 =====
|
||
REDIS_HOST=localhost
|
||
REDIS_PORT=6379
|
||
REDIS_PASSWORD=
|
||
REDIS_DB=0
|
||
|
||
# ===== PostgreSQL配置 =====
|
||
POSTGRES_HOST=localhost
|
||
POSTGRES_PORT=5432
|
||
POSTGRES_USER=compliance
|
||
POSTGRES_PASSWORD=compliance123
|
||
POSTGRES_DB=compliance_db
|
||
|
||
# ===== 文档处理配置 =====
|
||
CHUNK_SIZE=512
|
||
CHUNK_OVERLAP=50
|
||
MAX_FILE_SIZE_MB=100
|
||
DOCUMENT_METADATA_PATH=backend/data/documents.json
|
||
PARSER_BACKEND=aliyun
|
||
CHUNK_BACKEND=aliyun
|
||
|
||
# ===== 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
|
||
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
|
||
|
||
# ===== 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
|
||
QWEN_MODEL=qwen3.6-plus
|
||
QWEN_VL_MODEL=qwen3-vl-plus
|
||
DEEPSEEK_MODEL=deepseek-v4-flash
|
||
|
||
# ===== RAG配置 =====
|
||
RAG_TOP_K=10
|
||
RAG_MAX_CONTEXT_TOKENS=4000
|
||
RAG_SUMMARY_MAX_TOKENS=1024
|
||
|
||
# ===== 会话配置 =====
|
||
SESSION_MAX_SESSIONS=100
|
||
SESSION_TIMEOUT_MINUTES=30
|