klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Changed multimodal prompt to extract better text from images (#2322)

Browse Source
This commit is contained in:
Prateek Chhikara
2025-03-06 11:57:20 -08:00
committed by GitHub
parent b701a50b51
commit c6fbba6a4d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
mem0/memory/utils.py
View File

@@ -57,7 +57,7 @@ def get_image_description(image_url):
"content": [ "content": [
{ {
"type": "text", "type": "text",
"text": "Provide a description of the image and do not include any additional text.", "text": "A user is providing an image. Provide a high level description of the image and do not include any additional text.",
}, },
{"type": "image_url", "image_url": {"url": image_url}}, {"type": "image_url", "image_url": {"url": image_url}},
], ],