AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-06-04 11:24:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: replace models of novita (#7360)

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

Replace models of novita

### Type of change

- [x] Other (please describe): Replace models of novita
This commit is contained in:
Neal Davis 2025-04-28 13:35:09 +08:00 committed by GitHub
parent af770c5ced
commit 23dcbc94ef
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 74 additions and 166 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

232
conf/llm_factories.json
View File

@ -2203,58 +2203,21 @@
]
},
{
"name": "novita.ai",
"name": "NovitaAI",
"logo": "",
"tags": "LLM,IMAGE2TEXT",
"tags": "LLM,TEXT EMBEDDING",
"status": "1",
"llm": [
{
"llm_name": "deepseek/deepseek-r1",
"tags": "LLM,CHAT,64k",
"max_tokens": 64000,
"model_type": "chat"
},
{
"llm_name": "deepseek/deepseek_v3",
"tags": "LLM,CHAT,64k",
"max_tokens": 64000,
"model_type": "chat"
},
{
"llm_name": "deepseek/deepseek-r1-distill-llama-70b",
"tags": "LLM,CHAT,64k",
"max_tokens": 64000,
"model_type": "chat"
},
{
"llm_name": "deepseek/deepseek-r1-distill-qwen-32b",
"tags": "LLM,CHAT,64k",
"max_tokens": 64000,
"model_type": "chat"
},
{
"llm_name": "deepseek/deepseek-r1-distill-qwen-14b",
"tags": "LLM,CHAT,64k",
"max_tokens": 64000,
"model_type": "chat"
},
{
"llm_name": "deepseek/deepseek-r1-distill-llama-8b",
"llm_name": "qwen/qwen2.5-7b-instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32000,
"model_type": "chat"
},
{
"llm_name": "meta-llama/llama-3.3-70b-instruct",
"tags": "LLM,CHAT,128k",
"max_tokens": 131072,
"model_type": "chat",
"is_tools": true
},
{
"llm_name": "meta-llama/llama-3.2-11b-vision-instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"llm_name": "meta-llama/llama-3.2-1b-instruct",
"tags": "LLM,CHAT,131k",
"max_tokens": 131000,
"model_type": "chat"
},
{
@ -2264,15 +2227,21 @@
"model_type": "chat"
},
{
"llm_name": "meta-llama/llama-3.2-1b-instruct",
"llm_name": "thudm/glm-4-9b-0414",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"max_tokens": 32000,
"model_type": "chat"
},
{
"llm_name": "meta-llama/llama-3.1-70b-instruct",
"llm_name": "thudm/glm-z1-9b-0414",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"max_tokens": 32000,
"model_type": "chat"
},
{
"llm_name": "meta-llama/llama-3.1-8b-instruct-bf16",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat",
"is_tools": true
},
@ -2284,55 +2253,15 @@
"is_tools": true
},
{
"llm_name": "meta-llama/llama-3.1-8b-instruct-bf16",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat",
"is_tools": true
},
{
"llm_name": "meta-llama/llama-3-70b-instruct",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat",
"is_tools": true
},
{
"llm_name": "meta-llama/llama-3-8b-instruct",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat",
"is_tools": true
},
{
"llm_name": "qwen/qwen-2.5-72b-instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32000,
"model_type": "chat",
"is_tools": true
},
{
"llm_name": "qwen/qwen-2-vl-72b-instruct",
"tags": "LLM,IMAGE2TEXT,32k",
"max_tokens": 32768,
"model_type": "image2text"
},
{
"llm_name": "qwen/qwen-2-7b-instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "mistralai/mistral-nemo",
"llm_name": "deepseek/deepseek-v3-0324",
"tags": "LLM,CHAT,128k",
"max_tokens": 131072,
"max_tokens": 128000,
"model_type": "chat"
},
{
"llm_name": "mistralai/mistral-7b-instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"llm_name": "deepseek/deepseek-r1-turbo",
"tags": "LLM,CHAT,64k",
"max_tokens": 64000,
"model_type": "chat"
},
{
@ -2342,82 +2271,61 @@
"model_type": "chat"
},
{
"llm_name": "sao10k/l3-70b-euryale-v2.1",
"llm_name": "meta-llama/llama-3.3-70b-instruct",
"tags": "LLM,CHAT,128k",
"max_tokens": 131072,
"model_type": "chat",
"is_tools": true
},
{
"llm_name": "deepseek/deepseek-r1-distill-llama-8b",
"tags": "LLM,CHAT,32k",
"max_tokens": 32000,
"model_type": "chat"
},
{
"llm_name": "mistralai/mistral-nemo",
"tags": "LLM,CHAT,128k",
"max_tokens": 131072,
"model_type": "chat"
},
{
"llm_name": "meta-llama/llama-3-8b-instruct",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat",
"is_tools": true
},
{
"llm_name": "deepseek/deepseek-v3-turbo",
"tags": "LLM,CHAT,64k",
"max_tokens": 64000,
"model_type": "chat",
"is_tools": true
},
{
"llm_name": "mistralai/mistral-7b-instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "sao10k/l3-8b-lunaris",
"tags": "LLM,CHAT,8k",
"llm_name": "deepseek/deepseek-r1",
"tags": "LLM,CHAT,64k",
"max_tokens": 64000,
"model_type": "chat"
},
{
"llm_name": "deepseek/deepseek-r1-distill-qwen-14b",
"tags": "LLM,CHAT,64k",
"max_tokens": 64000,
"model_type": "chat"
},
{
"llm_name": "baai/bge-m3",
"tags": "TEXT EMBEDDING,8K",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "sao10k/l31-70b-euryale-v2.2",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "nousresearch/hermes-2-pro-llama-3-8b",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "nousresearch/nous-hermes-llama2-13b",
"tags": "LLM,CHAT,4k",
"max_tokens": 4096,
"model_type": "chat"
},
{
"llm_name": "openchat/openchat-7b",
"tags": "LLM,CHAT,4k",
"max_tokens": 4096,
"model_type": "chat"
},
{
"llm_name": "gryphe/mythomax-l2-13b",
"tags": "LLM,CHAT,4k",
"max_tokens": 4096,
"model_type": "chat"
},
{
"llm_name": "microsoft/wizardlm-2-8x22b",
"tags": "LLM,CHAT,65k",
"max_tokens": 65535,
"model_type": "chat"
},
{
"llm_name": "google/gemma-2-9b-it",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "cognitivecomputations/dolphin-mixtral-8x22b",
"tags": "LLM,CHAT,16k",
"max_tokens": 16000,
"model_type": "chat"
},
{
"llm_name": "jondurbin/airoboros-l2-70b",
"tags": "LLM,CHAT,4k",
"max_tokens": 4096,
"model_type": "chat"
},
{
"llm_name": "teknium/openhermes-2.5-mistral-7b",
"tags": "LLM,CHAT,4k",
"max_tokens": 4096,
"model_type": "chat"
},
{
"llm_name": "sophosympatheia/midnight-rose-70b",
"tags": "LLM,CHAT,4k",
"max_tokens": 4096,
"model_type": "chat"
"model_type": "embedding"
}
]
},

2
docs/references/supported_models.mdx
View File

@ -37,7 +37,7 @@ A complete list of models supported by RAGFlow, which will continue to expand.
| Mistral | :heavy_check_mark: | :heavy_check_mark: | | | | |
| ModelScope | :heavy_check_mark: | | | | | |
| Moonshot | :heavy_check_mark: | | | :heavy_check_mark: | | |
| novita.ai | :heavy_check_mark: | | | | | |
| Novita AI | :heavy_check_mark: | :heavy_check_mark: | | | | |
| NVIDIA | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| 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: |

2
docs/release_notes.md
View File

@ -412,7 +412,7 @@ Released on August 26, 2024.
- Incorporates monitoring for the task executor.
- Introduces Agent tools **GitHub**, **DeepL**, **BaiduFanyi**, **QWeather**, and **GoogleScholar**.
- Supports chunking of EML files.
- Supports more LLMs or model services: **GPT-4o-mini**, **PerfXCloud**, **TogetherAI**, **Upstage**, **Novita.AI**, **01.AI**, **SiliconFlow**, **PPIO**, **XunFei Spark**, **Baidu Yiyan**, and **Tencent Hunyuan**.
- Supports more LLMs or model services: **GPT-4o-mini**, **PerfXCloud**, **TogetherAI**, **Upstage**, **Novita AI**, **01.AI**, **SiliconFlow**, **PPIO**, **XunFei Spark**, **Baidu Yiyan**, and **Tencent Hunyuan**.
## v0.9.0

2
rag/llm/__init__.py
View File

@ -234,7 +234,7 @@ ChatModel = {
"TogetherAI": TogetherAIChat,
"PerfXCloud": PerfXCloudChat,
"Upstage": UpstageChat,
"novita.ai": NovitaAIChat,
"NovitaAI": NovitaAIChat,
"SILICONFLOW": SILICONFLOWChat,
"PPIO": PPIOChat,
"01.AI": YiChat,

2
web/src/constants/llm.ts
View File

@ -28,7 +28,7 @@ export enum LLMFactory {
TogetherAI = 'TogetherAI',
PerfXCloud = 'PerfXCloud',
Upstage = 'Upstage',
NovitaAI = 'novita.ai',
NovitaAI = 'NovitaAI',
SILICONFLOW = 'SILICONFLOW',
PPIO = 'PPIO',
ZeroOneAI = '01.AI',