You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
SimpleChatTC:FetchPdfAsText: Renamed function call
Some ai's dont seem to be prefering to use this direct helper
provided for fetching pdf as text, on its own. Instead ai (gptoss)
seems to be keen on fetching raw pdf and extract text etal, so now
renaming the function call to try and make its semantic more
readily obivious hopefully.
It sometimes (not always) seem to assum fetch_web_url_text, can
convert pdf to text and return it. Maybe I need to place the
specific fetch pdf as text before the generic fetch web url text
and so...
With the rename, the pdf specific fetch seems to be getting used
more.
Copy file name to clipboardExpand all lines: tools/server/public_simplechat/toolweb.mjs
+13-13Lines changed: 13 additions & 13 deletions
Original file line number
Diff line number
Diff line change
@@ -280,21 +280,21 @@ async function searchwebtext_setup(tcs) {
280
280
281
281
282
282
//
283
-
// PdfText
283
+
// FetchPdfText
284
284
//
285
285
286
286
287
-
letpdftext_meta={
287
+
letfetchpdftext_meta={
288
288
"type": "function",
289
289
"function": {
290
-
"name": "pdf_to_text",
291
-
"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. One is allowed to get a part of the pdf by specifying the starting and ending page numbers",
290
+
"name": "fetch_pdf_as_text",
291
+
"description": "Fetch 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. One is allowed to get a part of the pdf by specifying the starting and ending page numbers",
292
292
"parameters": {
293
293
"type": "object",
294
294
"properties": {
295
295
"url":{
296
296
"type":"string",
297
-
"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"
297
+
"description":"local file path (file://) / web (http/https) based url of the pdf that will be got and inturn converted to text"
298
298
},
299
299
"startPageNumber":{
300
300
"type":"integer",
@@ -312,7 +312,7 @@ let pdftext_meta = {
312
312
313
313
314
314
/**
315
-
* Implementation of the pdf to text logic.
315
+
* Implementation of the fetch pdf as text logic.
316
316
* Expects a simple minded proxy server to be running locally
0 commit comments