mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-01-04 03:25:30 +08:00
Specify img2text model by tag (#5063)
### What problem does this PR solve? The current design is not well-suited for multimodal models, as each model can only be configured for a single purpose—either chat or Img2txt. To work around this limitation, we use model aliases such as gpt-4o-mini and gpt-4o-mini-2024-07-18. To fix this, this PR allows specifying the Img2txt model by tag instead of model_type. ### Type of change - [x] Refactoring
This commit is contained in:
@ -8,13 +8,13 @@
|
||||
"llm": [
|
||||
{
|
||||
"llm_name": "gpt-4o-mini",
|
||||
"tags": "LLM,CHAT,128K",
|
||||
"tags": "LLM,CHAT,128K,IMAGE2TEXT",
|
||||
"max_tokens": 128000,
|
||||
"model_type": "chat"
|
||||
},
|
||||
{
|
||||
"llm_name": "gpt-4o",
|
||||
"tags": "LLM,CHAT,128K",
|
||||
"tags": "LLM,CHAT,128K,IMAGE2TEXT",
|
||||
"max_tokens": 128000,
|
||||
"model_type": "chat"
|
||||
},
|
||||
@ -72,18 +72,6 @@
|
||||
"max_tokens": 32768,
|
||||
"model_type": "chat"
|
||||
},
|
||||
{
|
||||
"llm_name": "gpt-4o-2024-08-06",
|
||||
"tags": "LLM,CHAT,IMAGE2TEXT",
|
||||
"max_tokens": 128000,
|
||||
"model_type": "image2text"
|
||||
},
|
||||
{
|
||||
"llm_name": "gpt-4o-mini-2024-07-18",
|
||||
"tags": "LLM,CHAT,IMAGE2TEXT",
|
||||
"max_tokens": 128000,
|
||||
"model_type": "image2text"
|
||||
},
|
||||
{
|
||||
"llm_name": "tts-1",
|
||||
"tags": "TTS",
|
||||
|
||||
Reference in New Issue
Block a user