pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2026-02-07 19:15:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

Refa: make RAGFlow more asynchronous (#11601)

Browse Source 
### What problem does this PR solve?

Try to make this more asynchronous. Verified in chat and agent
scenarios, reducing blocking behavior. #11551, #11579.

However, the impact of these changes still requires further
investigation to ensure everything works as expected.

### Type of change

- [x] Refactoring
This commit is contained in:
Yongteng Lei
2025-12-01 14:24:06 +08:00
committed by GitHub
parent 6ea4248bdc
commit b6c4722687
36 changed files with 1162 additions and 359 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
rag/llm/__init__.py
View File

@ -50,6 +50,7 @@ class SupportedLiteLLMProvider(StrEnum):
GiteeAI = "GiteeAI"
AI_302 = "302.AI"
JiekouAI = "Jiekou.AI"
ZHIPU_AI = "ZHIPU-AI"
FACTORY_DEFAULT_BASE_URL = {
@ -71,6 +72,7 @@ FACTORY_DEFAULT_BASE_URL = {
SupportedLiteLLMProvider.AI_302: "https://api.302.ai/v1",
SupportedLiteLLMProvider.Anthropic: "https://api.anthropic.com/",
SupportedLiteLLMProvider.JiekouAI: "https://api.jiekou.ai/openai",
SupportedLiteLLMProvider.ZHIPU_AI: "https://open.bigmodel.cn/api/paas/v4",
}
@ -102,6 +104,7 @@ LITELLM_PROVIDER_PREFIX = {
SupportedLiteLLMProvider.GiteeAI: "openai/",
SupportedLiteLLMProvider.AI_302: "openai/",
SupportedLiteLLMProvider.JiekouAI: "openai/",
SupportedLiteLLMProvider.ZHIPU_AI: "openai/",
}
ChatModel = globals().get("ChatModel", {})