pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2026-02-04 17:45:07 +08:00
Code Issues Packages Projects Releases Wiki Activity

Feat: Support vLLM #4316 (#5395)

Browse Source 
### What problem does this PR solve?
Feat: Support vLLM #4316

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
balibabu
2025-02-26 18:33:43 +08:00
committed by GitHub
parent fefea3a2a5
commit d9dd1171a3
9 changed files with 235 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
web/src/pages/user-setting/setting-model/ollama-modal/index.tsx
View File

@ -1,3 +1,4 @@
import { LLMFactory } from '@/constants/llm';
import { useTranslate } from '@/hooks/common-hooks';
import { IModalProps } from '@/interfaces/common';
import { IAddLlmRequestBody } from '@/interfaces/request/llm';
@ -18,19 +19,23 @@ type FieldType = IAddLlmRequestBody & { vision: boolean };
const { Option } = Select;
const llmFactoryToUrlMap = {
Ollama:
[LLMFactory.Ollama]:
'https://github.com/infiniflow/ragflow/blob/main/docs/guides/deploy_local_llm.mdx',
Xinference: 'https://inference.readthedocs.io/en/latest/user_guide',
ModelScope: 'https://www.modelscope.cn/docs/model-service/API-Inference/intro',
LocalAI: 'https://localai.io/docs/getting-started/models/',
'LM-Studio': 'https://lmstudio.ai/docs/basics',
'OpenAI-API-Compatible': 'https://platform.openai.com/docs/models/gpt-4',
TogetherAI: 'https://docs.together.ai/docs/deployment-options',
Replicate: 'https://replicate.com/docs/topics/deployments',
OpenRouter: 'https://openrouter.ai/docs',
HuggingFace:
[LLMFactory.Xinference]:
'https://inference.readthedocs.io/en/latest/user_guide',
[LLMFactory.ModelScope]:
'https://www.modelscope.cn/docs/model-service/API-Inference/intro',
[LLMFactory.LocalAI]: 'https://localai.io/docs/getting-started/models/',
[LLMFactory.LMStudio]: 'https://lmstudio.ai/docs/basics',
[LLMFactory.OpenAiAPICompatible]:
'https://platform.openai.com/docs/models/gpt-4',
[LLMFactory.TogetherAI]: 'https://docs.together.ai/docs/deployment-options',
[LLMFactory.Replicate]: 'https://replicate.com/docs/topics/deployments',
[LLMFactory.OpenRouter]: 'https://openrouter.ai/docs',
[LLMFactory.HuggingFace]:
'https://huggingface.co/docs/text-embeddings-inference/quick_tour',
GPUStack: 'https://docs.gpustack.ai/latest/quickstart',
[LLMFactory.GPUStack]: 'https://docs.gpustack.ai/latest/quickstart',
[LLMFactory.VLLM]: 'https://docs.vllm.ai/en/latest/',
};
type LlmFactory = keyof typeof llmFactoryToUrlMap;
@ -66,11 +71,11 @@ const OllamaModal = ({
llmFactoryToUrlMap[llmFactory as LlmFactory] ||
'https://github.com/infiniflow/ragflow/blob/main/docs/guides/deploy_local_llm.mdx';
const optionsMap = {
HuggingFace: [
[LLMFactory.HuggingFace]: [
{ value: 'embedding', label: 'embedding' },
{ value: 'chat', label: 'chat' },
],
Xinference: [
[LLMFactory.Xinference]: [
{ value: 'chat', label: 'chat' },
{ value: 'embedding', label: 'embedding' },
{ value: 'rerank', label: 'rerank' },
@ -78,10 +83,8 @@ const OllamaModal = ({
{ value: 'speech2text', label: 'sequence2text' },
{ value: 'tts', label: 'tts' },
],
ModelScope: [
{ value: 'chat', label: 'chat' },
],
GPUStack: [
[LLMFactory.ModelScope]: [{ value: 'chat', label: 'chat' }],
[LLMFactory.GPUStack]: [
{ value: 'chat', label: 'chat' },
{ value: 'embedding', label: 'embedding' },
{ value: 'rerank', label: 'rerank' },