pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: Gemini parameters error (#9520)

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

Fix Gemini parameters error.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
This commit is contained in:
Yongteng Lei
2025-08-18 14:51:10 +08:00
committed by GitHub
parent 5808aef28c
commit fe32952825
2 changed files with 13 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
conf/llm_factories.json
View File

@ -1146,60 +1146,35 @@
"llm_name": "gemini-2.5-flash", "llm_name": "gemini-2.5-flash",
"tags": "LLM,CHAT,1024K,IMAGE2TEXT", "tags": "LLM,CHAT,1024K,IMAGE2TEXT",
"max_tokens": 1048576, "max_tokens": 1048576,
"model_type": "image2text", "model_type": "chat",
"is_tools": true "is_tools": true
}, },
{ {
"llm_name": "gemini-2.5-pro", "llm_name": "gemini-2.5-pro",
"tags": "LLM,CHAT,IMAGE2TEXT,1024K", "tags": "LLM,CHAT,IMAGE2TEXT,1024K",
"max_tokens": 1048576, "max_tokens": 1048576,
"model_type": "image2text", "model_type": "chat",
"is_tools": true "is_tools": true
}, },
{ {
"llm_name": "gemini-2.5-flash-preview-05-20", "llm_name": "gemini-2.5-flash-lite",
"tags": "LLM,CHAT,1024K,IMAGE2TEXT", "tags": "LLM,CHAT,1024K,IMAGE2TEXT",
"max_tokens": 1048576, "max_tokens": 1048576,
"model_type": "image2text", "model_type": "chat",
"is_tools": true "is_tools": true
}, },
{ {
"llm_name": "gemini-2.0-flash-001", "llm_name": "gemini-2.0-flash",
"tags": "LLM,CHAT,1024K",
"max_tokens": 1048576,
"model_type": "image2text",
"is_tools": true
},
{
"llm_name": "gemini-2.0-flash-thinking-exp-01-21",
"tags": "LLM,CHAT,1024K", "tags": "LLM,CHAT,1024K",
"max_tokens": 1048576, "max_tokens": 1048576,
"model_type": "chat", "model_type": "chat",
"is_tools": true "is_tools": true
}, },
{ {
"llm_name": "gemini-1.5-flash", "llm_name": "gemini-2.0-flash-lite",
"tags": "LLM,IMAGE2TEXT,1024K", "tags": "LLM,CHAT,1024K",
"max_tokens": 1048576, "max_tokens": 1048576,
"model_type": "image2text" "model_type": "chat",
},
{
"llm_name": "gemini-2.5-pro-preview-05-06",
"tags": "LLM,IMAGE2TEXT,1024K",
"max_tokens": 1048576,
"model_type": "image2text"
},
{
"llm_name": "gemini-1.5-pro",
"tags": "LLM,IMAGE2TEXT,2048K",
"max_tokens": 2097152,
"model_type": "image2text"
},
{
"llm_name": "gemini-1.5-flash-8b",
"tags": "LLM,IMAGE2TEXT,1024K",
"max_tokens": 1048576,
"model_type": "image2text",
"is_tools": true "is_tools": true
}, },
{ {

10
rag/llm/cv_model.py
View File

@ -539,24 +539,24 @@ class GeminiCV(Base):
return res.text, res.usage_metadata.total_token_count return res.text, res.usage_metadata.total_token_count
def chat(self, system, history, gen_conf, images=[]): def chat(self, system, history, gen_conf, images=[]):
from transformers import GenerationConfig generation_config = dict(temperature=gen_conf.get("temperature", 0.3), top_p=gen_conf.get("top_p", 0.7))
try: try:
response = self.model.generate_content( response = self.model.generate_content(
self._form_history(system, history, images), self._form_history(system, history, images),
generation_config=GenerationConfig(temperature=gen_conf.get("temperature", 0.3), top_p=gen_conf.get("top_p", 0.7))) generation_config=generation_config)
ans = response.text ans = response.text
return ans, response.usage_metadata.total_token_count return ans, response.usage_metadata.total_token_count
except Exception as e: except Exception as e:
return "**ERROR**: " + str(e), 0 return "**ERROR**: " + str(e), 0
def chat_streamly(self, system, history, gen_conf, images=[]): def chat_streamly(self, system, history, gen_conf, images=[]):
from transformers import GenerationConfig
ans = "" ans = ""
response = None response = None
try: try:
generation_config = dict(temperature=gen_conf.get("temperature", 0.3), top_p=gen_conf.get("top_p", 0.7))
response = self.model.generate_content( response = self.model.generate_content(
self._form_history(system, history, images), self._form_history(system, history, images),
generation_config=GenerationConfig(temperature=gen_conf.get("temperature", 0.3), top_p=gen_conf.get("top_p", 0.7)), generation_config=generation_config,
stream=True, stream=True,
) )
@ -572,7 +572,7 @@ class GeminiCV(Base):
yield response.usage_metadata.total_token_count yield response.usage_metadata.total_token_count
else: else:
yield 0 yield 0
class NvidiaCV(Base): class NvidiaCV(Base):
_FACTORY_NAME = "NVIDIA" _FACTORY_NAME = "NVIDIA"