AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-14 03:55:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

Feat: add VLLM (#5380)

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

Read to add VLMM.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Yongteng Lei 2025-02-26 16:04:53 +08:00 committed by GitHub
parent 96e9d50060
commit cdcaae17c6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
api/apps/llm_app.py
View File

@ -172,6 +172,10 @@ def add_llm():
llm_name = req["llm_name"] + "___OpenAI-API"
api_key = req.get("api_key", "xxxxxxxxxxxxxxx")
elif factory == "VLLM":
llm_name = req["llm_name"] + "___OpenAI-API"
api_key = req.get("api_key", "xxxxxxxxxxxxxxx")
elif factory == "XunFei Spark":
llm_name = req["llm_name"]
if req["model_type"] == "chat":

7
conf/llm_factories.json
View File

@ -316,6 +316,13 @@
"status": "1",
"llm": []
},
{
"name": "VLLM",
"logo": "",
"tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",
"status": "1",
"llm": []
},
{
"name": "Moonshot",
"logo": "",

1
docs/references/supported_models.mdx
View File

@ -42,6 +42,7 @@ A complete list of models supported by RAGFlow, which will continue to expand.
| Ollama | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | | |
| OpenAI | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
| OpenAI-API-Compatible | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| VLMM | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| OpenRouter | :heavy_check_mark: | | | :heavy_check_mark: | | |
| PerfXCloud | :heavy_check_mark: | :heavy_check_mark: | | | | |
| Replicate | :heavy_check_mark: | :heavy_check_mark: | | | | |

4
rag/llm/__init__.py
View File

@ -160,6 +160,7 @@ EmbeddingModel = {
"NVIDIA": NvidiaEmbed,
"LM-Studio": LmStudioEmbed,
"OpenAI-API-Compatible": OpenAI_APIEmbed,
"VLLM": OpenAI_APIEmbed,
"Cohere": CoHereEmbed,
"TogetherAI": TogetherAIEmbed,
"PerfXCloud": PerfXCloudEmbed,
@ -188,6 +189,7 @@ CvModel = {
"LM-Studio": LmStudioCV,
"StepFun": StepFunCV,
"OpenAI-API-Compatible": OpenAI_APICV,
"VLLM": OpenAI_APICV,
"TogetherAI": TogetherAICV,
"01.AI": YiCV,
"Tencent Hunyuan": HunyuanCV,
@ -215,6 +217,7 @@ ChatModel = {
"NVIDIA": NvidiaChat,
"LM-Studio": LmStudioChat,
"OpenAI-API-Compatible": OpenAI_APIChat,
"VLLM": OpenAI_APIChat,
"Cohere": CoHereChat,
"LeptonAI": LeptonAIChat,
"TogetherAI": TogetherAIChat,
@ -244,6 +247,7 @@ RerankModel = {
"NVIDIA": NvidiaRerank,
"LM-Studio": LmStudioRerank,
"OpenAI-API-Compatible": OpenAI_APIRerank,
"VLLM": OpenAI_APIRerank,
"Cohere": CoHereRerank,
"TogetherAI": TogetherAIRerank,
"SILICONFLOW": SILICONFLOWRerank,