Comments (17)
it works now, i installed via melpa
from gptel.
Hi @randomwangran,
I just added a debug setting to diagnose issues like this. Could you
-
Pull the latest from this repo and install/load it,
-
Run
(setq gptel--debug t)
before running gptel, -
Run gptel and wait for a buffer named
*gptel-error*
response to pop up, -
and paste the contents of the buffer here?
If no such buffer pops up, that's helpful too and you can let me know.
from gptel.
I ran the code, waited several minutes, and no error buffer popped up.
from gptel.
@jmercouris Thank you. Is the value of gptel-use-curl
non-nil for you? (It might look like /usr/bin/curl
)
from gptel.
gptel-use-curl is a variable defined in ‘gptel.el’.
Its value is t
Whether gptel should prefer Curl when available.
You can customize this variable.
from gptel.
Please note:
[jmercouris@system:~/.emacs.d/packages]$ which curl
/run/current-system/sw/bin/curl
I am running NixOS.
from gptel.
Could you set gptel-use-curl
to nil
and check if the problem persists?
from gptel.
The same problem. And set gptel-use-curl
in gptel.el
to nil
couldn't solve the problem.
from gptel.
@ydche3 Could you try again (with gptel--debug
set to t
)? I removed the aio dependency and made the code simpler to debug in 040baad.
from gptel.
@ydche3 Could you try again (with
gptel--debug
set tot
)? I removed the aio dependency and made the code simpler to debug in 040baad.
Without any difference. But I noticed that whenever run C-c RET
to send my query, the request wasn't sent behind my proxy.
Here is my emacs proxy setting:
(setq url-proxy-services '(("http" . "127.0.0.1:7890")
("https" . "127.0.0.1:7890")))
Should I change my proxy setting?
BTW, I've tried an other openai plugin under my proxy setting, and it works.
from gptel.
You shouldn't have to change your proxy settings. Did you notice this with gptel-use-curl
set to nil
, t
or both?
from gptel.
I have the same problem, it worked first when I tried the mode 4 days ago, but when I tried again today it doesnt return any answers.
I set: "(setq gptel--debug t)"
Where should that info be displayed? (no new buffer with messages with gptel atleast).
When I call the same api end point with javascript and axios, I get answers so it shouldnt be a open ai api problem.
EDIT: Never mind, had to re-read the README - didnt do "M-x gptel-send" this time :)
from gptel.
EDIT: Never mind, had to re-read the README - didnt do "M-x gptel-send" this time :)
Please let me know if the README could be worded better.
from gptel.
No the readme was clear, it was my bad not re-reading it again.
Thank you for the work on this mode!
EDIT: Maybe could add that you need to do gptel-send here:
Like ChatGPT ready - Hint: Dont forget to do gptel-send
I expected the second time when I write the question after ### and press enter, it will send the query.
Don't know emacs too well, to know is this is hard to implement.
from gptel.
Like ChatGPT ready - Hint: Dont forget to do gptel-send
The package already does this, I'm not sure what you mean. Here is what I see:
from gptel.
@jmercouris do you still see this error?
from gptel.
Like ChatGPT ready - Hint: Dont forget to do gptel-send
@flashjames I'm closing this issue since the original problem has been solved and this hinting is addressed as well. Feel free to reopen if this is not the case.
from gptel.
Related Issues (20)
- gptel-org-branching-context requires Org 9.7 (unreleased) HOT 6
- Watermarking / inline annotation of LLM generated content vs prompt content HOT 2
- Org mode response formatting HOT 8
- Ollama as default backend HOT 1
- Perplexity: citations HOT 14
- Different results between gptel+ChatGPT and chat.openai.com HOT 2
- Auto Fill mode should be respected HOT 4
- Wrong language in the source block header HOT 4
- Help using local backends HOT 2
- Interacting with privateGPT (specifically for RAG) HOT 10
- Is it possible to interact with LLMs provided by an Open WebUI? HOT 1
- Error with the local LLM scripts in init file HOT 5
- How to disable the highlight after its done generating HOT 9
- How to register additional backends in doom emacs? HOT 5
- Enhance `gptel` to allow selecting from list of existing gptel buffers, when called interactively HOT 1
- [enhancement] Provide information about the different models HOT 1
- Updating `DoomEmacs`/`gptel` and chaing lightly configuration => only garbage generated now... HOT 8
- (gptel-menu) Truncated width of system message is wrong
- Better prefix-arg behavior for M-x gptel
- gptel-request wrong type argument HOT 7
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from gptel.