Chris,
Congratulations!! You have just drove me out of this forum for good with you blah, blah, blah.
I blame myself for having come here in the first place.
Let me be clear: We do not want asynchropnous processing for this - Do you understand?
I take offense by you saying we are not providing a concrete solution. Who do you think you are?
Gerrit,
You can get away with not using COM code page translation with some latin based languages (e.g. Dutch), but what Chris was saying is correct:
It would mainly render the text you want to translate wrong, but AI might fix that flaw by having seen wrong codepage letters in the data it was...
Chris,
Why (4?): Have you ever seen the nasty "Visual Foxpro not responding" titlebar message when long processes are running? We use this COM EXE for many many things. Did you notice the CASE statement? We have other CASEs where GetOpenAIResponseText is called (e.g. OpenAI Text Generation)...
Gerrit,
Here are a few tips which may help:
(1) It is highly recommended that you use the temperature and top_p parameters in the JSON request as show in the above post to Manni. Otherwise, both will default to 1 which can result in bizzare or incomplete translations.
It's also important to...
Another thing very cool with OpenAI language translation is that it can be used to correct grammar and spelling - just translate a language to itself:
"Translate the following text from English to English"
This can be done with any language.
Gerrit,
How are you rendering translated text? You know that UTF-8 is required and that VFP does not natively UTF-8. For example, you can capture a translation to a file and view it in Notepad which does supports UTF-8. See below for a English to Hindi translation:
But how can you translate...
ManniB,
A couple of things here:
(1) Gerrit is talking about using the OpenAI API to write VFP code for language translation "completion". This is not ChatGTP - they are two different animals. For example, with the API you can translate a few thousand words of Spanish > Thai > Korean >...
Gerrit,
With respect to Vision, we learned in the OpenAI forums that it is best to resize a base64 image (or images) before it is sent. See this:
We can provide the code for this - You may want to modify if you don't need tcDetail, tcDimension, or tiBytes info
*!* Resizes a image...
Hi Gerrit,
When you are ready to tackle language translation, you should start another thread.
As of this writing, we have successfully implemented six OpenAI services for a client: (1) DALL-E-3 Image generation; (2) Text generation; (3) Speech-To-Text; (4) Text-To-Speech; (5) Vision; and (6)...
Gerrit,
Yes, the API's interpretation of the text prompt is tricky - must be precise with Vision.
Here is some good news: Yesterday, OpenAI released a new model: GPT-4o (“o” for “omni”). You can use it now - just replace "gpt-4-turbo" with "gpt-4o"
See here...
Almost forgot,
Last night, I ran a "face recognition" test sending 10 base64 images - the images were from my brother's wedding where there were hundreds of people:
lcDirective = "Please provide a response without using any asterisks (*) or pound signs (#). For headings, prepend only with...
Here is what I came up with - similar to yours, but no curly brackets around <<lcBase64Image>>
TEXT TO lcRequest TEXTMERGE NOSHOW
{"model": "gpt-4-turbo",
"messages": [{"role": "system","content": "<<lcDirective>>"},
{"role": "user", "content":
[{"type": "text"...
Gerrit,
Since you are getting good results for an OCR, could you please provide the VFP code for the JSON request? Since it's an OCR, I'm assuming you are using a local base64 image and not a URL, right?
I'm having a very hard time understanding what is being accomplished in this thread - I thought it was supposed to be about GPT-4 Turbo with Vision, not ChatGPT.
First of all, it appears that GPT-4 Turbo with Vision does not support OCR. See here...
ManniB,
A ChatGPT subscription is different from an OpenAI API account - they are seperate services. While OpenAI owns ChatGPT, ChatGPT is a subset of the models that are available for the OpenAI API.
ManniB,
OpenAI Sora (text-to-video) will be released to the public later this year: https://openai.com/sora#research
I am not sure what you mean by data security/privacy issues. Can you be more explicit? As far as I know, in addition to AI's ability to take peoples jobs, there are potential...
ManniB,
CREATEBINARY(lcRequest) works! yay! :) I saw Marco Plaza post early today, but forgot to try it.
Actually, the response was surprisingly fast compared to other OpenAI models we use.
Big thanks to you and everyone who responded.
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.