element.chen/ai-g3sb-backman2.0
1
0
Fork 0
Code Pull Requests Activity
Files
main
ai-g3sb-backman2.0/.env
T

78 lines
3.1 KiB
Bash
Raw Permalink Normal View History

first commit
2026-04-10 16:52:07 +08:00
# Text2SQL Agent 环境配置示例
# 复制为 .env 并填入实际值
# ========== DeepSeek API 配置 ==========
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
# LLM 路由（deepseek | openai），不填则按 Key 自动选择（优先 deepseek）
LLM_SERVICE_CODE=openai
DEEPSEEK_API_KEY=sk-041b3995415c4445a1713750fcc9e023
first commit
2026-04-10 16:52:07 +08:00
DEEPSEEK_BASE_URL=https://api.deepseek.com
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
MODEL_PRIMARY=deepseek-chat
OPENAI_API_KEY=sk-proj-FEb2ChHZK5Llm0tBkmNIT3BlbkFJbu0b0zQpTW8762yD6HDv
OPENAI_BASE_URL=http://113.192.49.54:9080/v1
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
2026-04-16 15:49:03 +08:00
OPENAI_MODEL=gpt-4o-mini
# OPENAI_CHAT_MODEL=
first commit
2026-04-10 16:52:07 +08:00
# 模型配置
# 主生成模型
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
2026-04-16 09:15:01 +08:00
first commit
2026-04-10 16:52:07 +08:00
TEMPERATURE=0 # 确定性模式：每次生成相同结果
MAX_TOKENS=4096
# 生成与校验默认 SQL Server（T-SQL）；可改为 mysql / postgresql 等
TEXT2SQL_DIALECT=sqlserver
Refactor embedding configuration to remove local model support, transitioning to a unified remote API approach. Update environment variables and documentation accordingly. Enhance error handling in the orchestrator and related modules to reflect these changes. This update simplifies the embedding process and improves overall system reliability.
2026-04-15 09:49:18 +08:00
# ========== Embedding 配置（远程 /v1/embeddings，须配置下方 OPENAI_* 或 MODELSCOPE_* 等）==========
first commit
2026-04-10 16:52:07 +08:00
# ModelScope 推理 API：https://www.modelscope.cn/docs/inference-api
# MODELSCOPE_API_KEY=ms-b95f3233-4797-4efd-90e6-b3728743571d
# MODELSCOPE_BASE_URL=https://api-inference.modelscope.cn/v1
# MODELSCOPE_EMBEDDING_MODEL=Qwen/Qwen3-Embedding-8B
# # 单次请求最大条数，按服务端限制调整
# MODELSCOPE_EMBEDDING_MAX_BATCH=32
# 兼容 OpenAI 的网关：地址含 /v1（若网关根路径即 OpenAI API 则按实际填写）
OPENAI_BASE_URL=http://113.192.49.54:9080/v1
OPENAI_API_KEY=sk-proj-FEb2ChHZK5Llm0tBkmNIT3BlbkFJbu0b0zQpTW8762yD6HDv
OPENAI_EMBEDDING_MODEL=text-embedding-ada-002
Enhance dialog context handling for Text2SQL queries by integrating session history. Introduce new methods for summarizing previous assistant messages and determining if the last interaction was a data query. Update environment configuration for embedding options and improve error handling in SQL generation. Add user-facing delivery messages for successful SQL execution. This update supports more coherent follow-up questions and improves user experience in conversational interactions.
2026-04-14 18:02:12 +08:00
# ========== 数据文件与向量库路径（均相对仓库根目录）==========
# G3SB 表结构；api_server 用 SCHEMA_PATH / SCHEMA_META_PATH（勿用 SCHEMA_FILE，代码不读）
SCHEMA_PATH=./data/schemas/G3SB_MCDataDictionary_table_structure.json
# G3SB 表注释，与 structure 同名配对；粗筛 embedding 文本会含表注释
SCHEMA_META_PATH=./data/schemas/G3SB_MCDataDictionary_table_meta.json
# Schema 表级向量持久化目录（Chroma 集合名固定为 schema_tables）；改 structure/meta 后需强制重建索引
first commit
2026-04-10 16:52:07 +08:00
VECTOR_DB_PATH=./data/embeddings/chroma
Enhance dialog context handling for Text2SQL queries by integrating session history. Introduce new methods for summarizing previous assistant messages and determining if the last interaction was a data query. Update environment configuration for embedding options and improve error handling in SQL generation. Add user-facing delivery messages for successful SQL execution. This update supports more coherent follow-up questions and improves user experience in conversational interactions.
2026-04-14 18:02:12 +08:00
# Few-shot 源 JSONL（build_fewshot_chroma_index.py 默认读此变量）
FEWSHOT_DATA_PATH=./data/experiences/all_samples.jsonl
# Few-shot 向量持久化目录（Chroma 集合名默认 fewshot_samples；勿与 VECTOR_DB_PATH 混用同一目录）
FEWSHOT_CHROMA_PATH=./data/embeddings/chroma_fewshot
first commit
2026-04-10 16:52:07 +08:00
# ========== 验证配置 ==========
ENABLE_SQL_VALIDATION=true
BLOCK_DANGEROUS_SQL=true
# ========== 重试配置 ==========
0.1.1 暂存
2026-04-14 10:28:22 +08:00
MAX_RETRY=2 # 确定性模式：只尝试一次，不重试
first commit
2026-04-10 16:52:07 +08:00
RETRY_DELAY=1.0
# ========== Few-shot 配置 ==========
# 是否启用经验数据集few-shot增强
FEWSHOT_ENABLED=true
# 每次使用的示例数量
FEWSHOT_TOP_K=3
# 示例最低评分（1-10）
FEWSHOT_MIN_RATING=7
Enhance dialog context handling for Text2SQL queries by integrating session history. Introduce new methods for summarizing previous assistant messages and determining if the last interaction was a data query. Update environment configuration for embedding options and improve error handling in SQL generation. Add user-facing delivery messages for successful SQL execution. This update supports more coherent follow-up questions and improves user experience in conversational interactions.
2026-04-14 18:02:12 +08:00
# 优先使用 Chroma 向量库（运行时检索不依赖 JSONL；灌库: python scripts/build_fewshot_chroma_index.py --force）
FEWSHOT_USE_CHROMA=true
# 留空则用代码默认集合名 fewshot_samples
FEWSHOT_CHROMA_COLLECTION=
first commit
2026-04-10 16:52:07 +08:00
# ========== 日志配置 ==========
LOG_LEVEL=INFO
0.1.1 暂存
2026-04-14 10:28:22 +08:00
LOG_FILE=./logs/text2sql.log
Enhance dialog context handling for Text2SQL queries by integrating session history. Introduce new methods for summarizing previous assistant messages and determining if the last interaction was a data query. Update environment configuration for embedding options and improve error handling in SQL generation. Add user-facing delivery messages for successful SQL execution. This update supports more coherent follow-up questions and improves user experience in conversational interactions.
2026-04-14 18:02:12 +08:00
# 业务库 SQLAlchemy URL（试执行探针 / dbhub）；也可用 DATABASE_URL
database_url=mssql+pymssql://sa:123456@192.168.3.201:1433/G3SB_PROD_HW
Copy Permalink