-
Notifications
You must be signed in to change notification settings - Fork 103
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
I cannot make gptstudio work with any API #215
Comments
When running local models with Ollama, it can sometimes take a long time for the model to be ready to be used. What model were you trying to use? Maybe try a smaller one like phi-3. |
Thank you.
I tried, but no, no response at all.
El sáb, 29 jun 2024 a las 5:04, James Wade ***@***.***>)
escribió:
… When running local models with Ollama, it can sometimes take a *long*
time for the model to be ready to be used. What model were you trying to
use? Maybe try a smaller one like phi-3.
—
Reply to this email directly, view it on GitHub
<#215 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AFI3FB4EFNLNOOYKIJNYUWTZJ2ICTAVCNFSM6AAAAABJGSLJGWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCOJYGEYDMNRSGQ>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
--
*Manuel Spínola, Ph.D.*
Instituto Internacional en Conservación y Manejo de Vida Silvestre
Universidad Nacional
Apartado 1350-3000
Heredia
COSTA RICA
***@***.*** ***@***.***>
***@***.***
Teléfono: (506) 8706 - 4662
Sitio web institucional: ICOMVIS
<http://www.icomvis.una.ac.cr/index.php/manuel>
Sitio web personal: Sitio personal <https://mspinola-sitioweb.netlify.app>
Blog sobre Ciencia de Datos: Blog de Ciencia de Datos
<https://mspinola-ciencia-de-datos.netlify.app>
|
What happens if you use openai? Do you get a response? Related to ollama: have you pulled any model? Do you get responses when using ollama directly in the terminal? |
Thank you.
I write in the terminal:
ollama pull phi
the Background Jobs screen looks like:
Loading required package: shiny
Listening on http://127.0.0.1:7905ℹ Fetching models for openai
service...✔ Got models!ℹ Fetching models for ollama service...✔ Got
models!
and when I try in gptstudio:::gptstudio_chat(), nothing happens.
El lun, 1 jul 2024 a las 7:19, Samuel Calderon ***@***.***>)
escribió:
… What happens if you use openai? Do you get a response?
Related to ollama: have you pulled any model? Do you get responses when
using ollama directly in the terminal?
—
Reply to this email directly, view it on GitHub
<#215 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AFI3FB5SNS6TZQAVQO7LK3DZKFJPLAVCNFSM6AAAAABJGSLJGWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEMBQGEZDGMBSGQ>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
--
*Manuel Spínola, Ph.D.*
Instituto Internacional en Conservación y Manejo de Vida Silvestre
Universidad Nacional
Apartado 1350-3000
Heredia
COSTA RICA
***@***.*** ***@***.***>
***@***.***
Teléfono: (506) 8706 - 4662
Sitio web institucional: ICOMVIS
<http://www.icomvis.una.ac.cr/index.php/manuel>
Sitio web personal: Sitio personal <https://mspinola-sitioweb.netlify.app>
Blog sobre Ciencia de Datos: Blog de Ciencia de Datos
<https://mspinola-ciencia-de-datos.netlify.app>
|
Hi, now is working with ollama, I follow the example Local Models with
Ollama • gptstudio (michelnivard.github.io)
<https://michelnivard.github.io/gptstudio/articles/ollama.html>.
What I did differently this time was to save as default like it showed in
the example.
El lun, 1 jul 2024 a las 7:19, Samuel Calderon ***@***.***>)
escribió:
… What happens if you use openai? Do you get a response?
Related to ollama: have you pulled any model? Do you get responses when
using ollama directly in the terminal?
—
Reply to this email directly, view it on GitHub
<#215 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AFI3FB5SNS6TZQAVQO7LK3DZKFJPLAVCNFSM6AAAAABJGSLJGWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEMBQGEZDGMBSGQ>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
--
*Manuel Spínola, Ph.D.*
Instituto Internacional en Conservación y Manejo de Vida Silvestre
Universidad Nacional
Apartado 1350-3000
Heredia
COSTA RICA
***@***.*** ***@***.***>
***@***.***
Teléfono: (506) 8706 - 4662
Sitio web institucional: ICOMVIS
<http://www.icomvis.una.ac.cr/index.php/manuel>
Sitio web personal: Sitio personal <https://mspinola-sitioweb.netlify.app>
Blog sobre Ciencia de Datos: Blog de Ciencia de Datos
<https://mspinola-ciencia-de-datos.netlify.app>
|
I'm sorry we weren't able to provide better help for this. This was hard to reproduce. I'm glad it is working for you now. Feel free to close the issue if you think you reached a solution, otherwise please provide further details. |
Confirm setup
{gptstudio}
(pak::pak("MichelNivard/gptstudio")
) and tested if the problem remains.{reprex}
and{sessioninfo}
packages to be able to run this issue's code snippetpak::pak(c("reprex", "sessioninfo"))
.What happened?
Sorry for this basic question, but I cannot make gpstudio work with any API. For example, Ollama:
ℹ Fetching models for ollama service...
✔ Got models!
I write a prompt:
make a plot with ggplot2
Nothing happens, no response at all.
Relevant log output
Session info
Created on 2024-06-12 with reprex v2.1.0
Session info
Code of Conduct
The text was updated successfully, but these errors were encountered: