panda
76f98a7aeb
- Add LLM_PROVIDER env var (openai/anthropic) to switch cloud backend - Use ChatAnthropic for anthropic provider with custom base_url - Add CONTEXT_MAX_TOKENS, CONTEXT_KEEP_RECENT, SESSIONS_DIR, HISTORY_MAX_SNAPSHOTS to .env and .env.example - Add langchain-anthropic dependency to requirements.txt Note: E2E testing blocked — the configured MiniMax API key (sk-cp-...) returns 401 across all endpoints (Anthropic and OpenAI). The API key may be expired or lack text-generation model access.
42 lines
919 B
Bash
42 lines
919 B
Bash
# 大语言模型后端：cloud 或 local
|
||
LLM_BACKEND=cloud
|
||
|
||
# 云端提供商：openai 或 anthropic
|
||
LLM_PROVIDER=openai
|
||
|
||
# 云端配置（OpenAI 兼容）
|
||
OPENAI_API_KEY=sk-xxxx
|
||
OPENAI_BASE_URL=https://api.openai.com/v1
|
||
LLM_MODEL=gpt-4o
|
||
|
||
# 本地大语言模型（Ollama）
|
||
LOCAL_LLM_MODEL=qwen2.5-coder:7b
|
||
|
||
# 嵌入模型后端：local 或 cloud
|
||
EMBED_BACKEND=local
|
||
LOCAL_EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
|
||
|
||
# 验证服务地址
|
||
VALIDATION_SERVICE_URL=http://localhost:8001/validate
|
||
|
||
# Chroma 持久化目录
|
||
CHROMA_PERSIST_DIR=./db/chroma
|
||
|
||
# 最大自动修正尝试次数
|
||
MAX_RETRY=3
|
||
|
||
# 上下文压缩阈值（token 数）
|
||
CONTEXT_MAX_TOKENS=6000
|
||
|
||
# 保留最近 N 轮完整对话
|
||
CONTEXT_KEEP_RECENT=4
|
||
|
||
# 会话持久化目录
|
||
SESSIONS_DIR=./sessions
|
||
|
||
# 状态快照保留数量（用于撤销操作）
|
||
HISTORY_MAX_SNAPSHOTS=10
|
||
|
||
# 意图识别模型（默认使用主 LLM 模型）
|
||
# INTENT_MODEL=gpt-4o-mini
|