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

Refactor:Improve BytesIO usage for GeminiCV (#10042)

Browse Source 
### What problem does this PR solve?
Improve BytesIO usage for GeminiCV

### Type of change
- [x] Refactoring
This commit is contained in:
Stephen Hu
2025-09-11 11:07:15 +08:00
committed by GitHub
parent 8a09f07186
commit 1936ad82d2
1 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
rag/llm/cv_model.py
View File

@ -521,24 +521,24 @@ class GeminiCV(Base):
else "Please describe the content of this picture, like where, when, who, what happen. If it has number data, please extract them out."
)
b64 = self.image2base64(image)
img = open(BytesIO(base64.b64decode(b64)))
input = [prompt, img]
res = self.model.generate_content(input)
img.close()
return res.text, res.usage_metadata.total_token_count
with BytesIO(base64.b64decode(b64)) as bio:
img = open(bio)
input = [prompt, img]
res = self.model.generate_content(input)
img.close()
return res.text, res.usage_metadata.total_token_count
def describe_with_prompt(self, image, prompt=None):
from PIL.Image import open
b64 = self.image2base64(image)
vision_prompt = prompt if prompt else vision_llm_describe_prompt()
img = open(BytesIO(base64.b64decode(b64)))
input = [vision_prompt, img]
res = self.model.generate_content(
input,
)
img.close()
return res.text, res.usage_metadata.total_token_count
with BytesIO(base64.b64decode(b64)) as bio:
img = open(bio)
input = [vision_prompt, img]
res = self.model.generate_content(input)
img.close()
return res.text, res.usage_metadata.total_token_count
def chat(self, system, history, gen_conf, images=[]):
generation_config = dict(temperature=gen_conf.get("temperature", 0.3), top_p=gen_conf.get("top_p", 0.7))