Files
ZNJJ-api-server/.env.example
T
Eric Wang e5d2a78886 feat(config): named LLM provider list via env vars, runtime selection
- Config.llm_profiles: LLM_PROVIDERS declares names, each group defined by
  LLM_<NAME>_BASE_URL/_API_KEY/_MODEL (required) and optional _TIMEOUT_SECONDS/
  _MAX_RETRIES/_TEMPERATURE/_EXTRA_BODY; JSON-dict form of LLM_PROVIDERS also
  supported. LLM_PROVIDER selects the active group at runtime; empty/fake =
  offline scripted model
- removed fixed openai/kimi groups (AGENT_LLM_PROVIDER, KIMI_LLM_*)
- validate(): incomplete groups and unknown LLM_PROVIDER fail fast with
  the configured-name list
- OpenAILLMService: http client trust_env from LLM_HTTP_TRUST_ENV (default
  False - local gateways must bypass the Windows system proxy)
- build_llm_service(provider): explicit name or LLM_PROVIDER default
- .env/.env.example: deepseek + kimi groups side by side, switch by
  LLM_PROVIDER=kimi (thinking off via EXTRA_BODY reasoning_effort=none)
- eval probe scripts updated to the new config interface

Verified: 172 unit tests; live calls succeed on both providers
(deepseek 28s, kimi 6.6s, both emitting valid <state> prefixes)
2026-10-22 13:59:18 +08:00

31 lines
1.2 KiB
Bash
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
DATABASE_URL=sqlite:///./test.db
SECRET_KEY=your_secret_key
DEBUG=True
ANALYSIS_SERVICE_URL=http://127.0.0.1:3030
ANALYSIS_AUTH_TOKEN=replace-with-fastgpt-api-key
APP_ID=replace-with-fastgpt-app-id
# Voice demo (Pipecat /ws-product). Relative to project root, or an absolute path.
VOICE_CONFIG=config/voice.json
# LangGraph chat backend(作业 2)
# AGENT_BACKEND=langgraph
#
# 命名 LLM 提供商组(均为 OpenAI 兼容接口):LLM_PROVIDERS 声明名单,
# LLM_PROVIDER 选择当前生效组;缺省或 fake = 离线脚本模型。
# 每组 LLM_<名>_BASE_URL / _API_KEY / _MODEL 必填;
# 可选 _TIMEOUT_SECONDS / _MAX_RETRIES / _TEMPERATURE / _EXTRA_BODY(JSON 字符串,
# 如思考开关 KIMI 网关为 {"reasoning_effort":"none"})。
# LLM_PROVIDERS=deepseek,kimi
# LLM_PROVIDER=deepseek
# LLM_DEEPSEEK_BASE_URL=https://api.openai.com/v1
# LLM_DEEPSEEK_API_KEY=replace-with-llm-api-key
# LLM_DEEPSEEK_MODEL=gpt-4o-mini
# LLM_KIMI_BASE_URL=http://127.0.0.1:3425/v1
# LLM_KIMI_API_KEY=magpie
# LLM_KIMI_MODEL=kimi-code-cn/kimi-for-coding
# LLM_KIMI_EXTRA_BODY={"reasoning_effort":"none"}
# 本地网关需直连(系统代理会导致 5xx);外部网关如需代理:
# LLM_HTTP_TRUST_ENV=true