happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

SimpleChatTC:Pdf2Text: Refine desc and MaxResultDataLength 

Needed to tweak the description further for the ai model to be
able to understand that its ok to pass file:// scheme based urls

Had forgotten how big the web site pages have become as also the
need for more ResultDataLength wrt one shot PDF read to get
atleast some good enough amount of content in it with large pdfs
This commit is contained in:
hanishkvc 2025-11-02 02:01:31 +05:30
parent 21544eaf87
commit e077f23f9e
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/public_simplechat/simplechat.js
View File

@ -1344,7 +1344,7 @@ class Me {
* Control the length of the tool call result data returned to ai after tool call.
* A value of 0 is treated as unlimited data.
*/
iResultMaxDataLength: 2048,
iResultMaxDataLength: 1024*128,
/**
* Control how many milliseconds to wait for tool call to respond, before generating a timed out
* error response and giving control back to end user.

4
tools/server/public_simplechat/toolweb.mjs
View File

@ -278,13 +278,13 @@ let pdf2text_meta = {
"type": "function",
"function": {
"name": "pdf2text",
"description": "Read pdf from requested local file / web url through a proxy server and return its text content after converting pdf to text, in few seconds",
"description": "Read pdf from requested local file path / web url through a proxy server and return its text content after converting pdf to text, in few seconds",
"parameters": {
"type": "object",
"properties": {
"url":{
"type":"string",
"description":"local file path / web (http/https) based url of the pdf that will be got and inturn converted to text to an extent"
"description":"local file path (file://) / web (http/https) based url of the pdf that will be got and inturn converted to text to an extent"
}
},
"required": ["url"]