ramonvc / freegpt-webui Goto Github PK
View Code? Open in Web Editor NEWGPT 3.5/4 with a Chat Web UI. No API key required.
Home Page: https://freegpt-webui-chimera.ramonvc.repl.co
License: GNU General Public License v3.0
GPT 3.5/4 with a Chat Web UI. No API key required.
Home Page: https://freegpt-webui-chimera.ramonvc.repl.co
License: GNU General Public License v3.0
python run.py
Running on http://127.0.0.1:1338
Running on http://192.168.10.5:1338
I can see the website. But when I type anything, it reads {"_action":"_ask","error":"an error occurred [Errno 11001] getaddrinfo failed","success":false}.
And the cmd reads:
[Errno 11001] getaddrinfo failed
What should I do?
your project is awsome! sadly i cant get it work to feed my chatgpt with data because it needs openai api
data.txt
我使用的是 docker run -p 1338:1338 ramonvc/freegpt-webui 构建的环境
对话后显示
{"_action":"_ask","error":"an error occurred timed out","success":false}
global.css
@import url("https://fonts.googleapis.com/css2?family=Inter:wght@100;200;300;400;500;600;700;800;900&display=swap");
:root {
--font-1: "Inter", sans-serif;
--section-gap: 20px;
--border-radius-1: 12px;
--colour-1: #ededed;
--colour-2: #000000;
--colour-3: #000000;
--colour-4: #000000;
--colour-5: #f4f4f4;
--colour-6: #d3d3d3;
--accent: #303030;
--blur-bg: #f4f4f4;
--blur-border: #e8e8e8;
--user-input: #000000;
--conversations: #555555;
}
* {
margin: 0;
padding: 0;
box-sizing: border-box;
position: relative;
font-family: var(--font-1);
}
html,
body {
background: var(--colour-1);
color: var(--colour-3);
}
ol,
ul {
padding-left: 40px;
}
.shown {
display: flex !important;
}
a:-webkit-any-link {
color: var(--accent);
}
@media screen and (max-height: 720px) {
:root {
--section-gap: 40px;
}
}
Hola, amigo! Impressive work! I couldn't get g4a to work and glad to see your repo.
One thing I found weird is that I checked your code which you already fixed that "always stays on gpt4" problem. Now we can switch between 3.5 and 4. However, it is showing the same result. Since I do not have a gpt4 access, can you try this problem for me?
"""
I have a box that can only transform coins, nothing else. If you insert a number of coins into it, the next day each coin will turn into 2 apples. Thus, if you add 3 coins there will be 6 apples after one day and 0 coins. I add 10 coins and wait for 3 days. What will happen?
"""
I switched 4 and 3.5 back and forth and they all are giving me the same result, 80 apples, which is wrong. The correct answer should be 20. I have seen other people implemented this and got succussed in GPT4.
Fully understand that it should be a forefront provider issue. How can we fix that tho? It will be quite pointless if this webhost is using 3.5 right? because everyone got access to 3.5. Or maybe not everyone but certainly everyone who is able to get on this github lol
who is the ceo of twitter?
{"_action":"_ask","error":"an error occurred HTTPSConnectionPool(host='ddg-api.herokuapp.com', port=443): Max retries exceeded with url: /search?query=who+is+the+ceo+of+twitter%3F&limit=5 (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x0000021F620C2650>, 'Connection to ddg-api.herokuapp.com timed out. (connect timeout=None)'))","success":false}
how to deal with this kind error??
Why can't I give the model an example "prompt" so that it knows how it will answer?
WIN 10运行第二条命令时报错, C:\WINDOWS\system32>docker run -p 1338:1338 ramonvc/freegpt-webui docker: 无效的containerPort: 1338:1338. 请参阅“docker run --help”。 无法打开 127.0.0.1:1338 网页
Or someone have?
As of yesterday, the backend takes a long time to think and returns an error...
"_action":"_ask","error":"an error occurred No scheme included in URL.","success":false
# Generate response
response = ChatCompletion.create(model=model, stream=True,
messages=messages, provider=g4f.Provider.Forefront)
This is a code snippet from file backend.py
If I understand correctly, this is the reason why any request goes to the Forefront provider, regardless of the selected model. This is why when we select GPT-4, we are actually using the same GPT-3.5 Turbo.
If you change the code to
response = ChatCompletion.create(model=model, stream=True,
messages=messages)
Then the Provider is taken from the file g4f/init.py:
class gpt_35_turbo:
name: str = 'gpt-3.5-turbo'
base_provider: str = 'openai'
best_site: Provider.Provider = Provider.Forefront
class gpt_4:
name: str = 'gpt-4'
base_provider: str = 'openai'
best_site: Provider.Provider = Provider.Bing
And now, the request is sent through the Provider Bing. But for some reason it's broken and I couldn't get any response.
docker: Error response from daemon: Ports are not available: exposing port TCP 0.0.0.0:1338 -> 0.0.0.0:0: listen tcp 0.0.0.0:1338: bind: An attempt was made to access a socket in a way forbidden by its access permissions.
Dear Ramonvc,
We have noticed that your program is accessing our LFG4 API (gpt.free.lsdev.me). On behalf of the LFG4 operations team, we would like to express our gratitude for your recognition.
However, the original intention of creating LFG4 was to provide a free platform for students who cannot afford the cost of PLUS users. Your use of our API consumes a considerable amount of resources, causing difficulties for those who truly need it.
Although we have increased our resources in the past two days, there are still widespread errors. Therefore, we have decided to restrict access for automated programs.
We apologize for any inconvenience this may cause.
Best wishes,
Gavin Wang
2023/07/08
I deployed the project on zeabur, and it is currently running with the default Docker setup. However, I need to make some modifications to the Dockerfile by adding "EXPOSE 1338" to expose the port. After making these changes, I can redeploy the project, and it will be accessible directly.
我在zeabur中部署了该项目,部署的时候默认是以docker启动的,但是需要修改一下Dockerfile文件,增加EXPOSE 1338,将端口暴露,之后再部署即可直接访问
how to updates from 0.08 to 0.10
GPT4 OFFLINE IN 0.08
BUT GPT4 IS ACTIVE IN 0.10
Can you tell me if the API interface of GPT4 is not available now? Will it also be unavailable in the future?
I can't use on my servers, but why you can
I deploy this project to my server , and set nginx.Today I find when I use website and ask a question, I will get a response like this. I this the origin web provider might set cloudflare to reject our request.
<!DOCTYPE html> <!--[if lt IE 7]> <html class="no-js ie6 oldie" lang="en-US"> <![endif]--> <!--[if IE 7]> <html class="no-js ie7 oldie" lang="en-US"> <![endif]--> <!--[if IE 8]> <html class="no-js ie8 oldie" lang="en-US"> <![endif]--> <!--[if gt IE 8]><!--> <html class="no-js" lang="en-US"> <!--<![endif]--> <head> <title>DNS resolution error | gpt.free.lsdev.me | Cloudflare</title> <meta charset="UTF-8" /> <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /> <meta http-equiv="X-UA-Compatible" content="IE=Edge" /> <meta name="robots" content="noindex, nofollow" /> <meta name="viewport" content="width=device-width,initial-scale=1" /> <link rel="stylesheet" id="cf_styles-css" href="/cdn-cgi/styles/main.css" />
<script> (function(){if(document.addEventListener&&window.XMLHttpRequest&&JSON&&JSON.stringify){var e=function(a){var c=document.getElementById("error-feedback-survey"),d=document.getElementById("error-feedback-success"),b=new XMLHttpRequest;a={event:"feedback clicked",properties:{errorCode:1001,helpful:a,version:1}};b.open("POST","https://sparrow.cloudflare.com/api/v1/event");b.setRequestHeader("Content-Type","application/json");b.setRequestHeader("Sparrow-Source-Key","c771f0e4b54944bebf4261d44bd79a1e"); b.send(JSON.stringify(a));c.classList.add("feedback-hidden");d.classList.remove("feedback-hidden")};document.addEventListener("DOMContentLoaded",function(){var a=document.getElementById("error-feedback"),c=document.getElementById("feedback-button-yes"),d=document.getElementById("feedback-button-no");"classList"in a&&(a.classList.remove("feedback-hidden"),c.addEventListener("click",function(){e(!0)}),d.addEventListener("click",function(){e(!1)}))})}})(); </script>
<script defer src="https://performance.radar.cloudflare.com/beacon.js"></script> </head> <body> <div id="cf-wrapper"> <div class="cf-alert cf-alert-error cf-cookie-error hidden" id="cookie-alert" data-translate="enable_cookies">Please enable cookies.</div> <div id="cf-error-details" class="p-0"> <header class="mx-auto pt-10 lg:pt-6 lg:px-8 w-240 lg:w-full mb-15 antialiased"> <h1 class="inline-block md:block mr-2 md:mb-2 font-light text-60 md:text-3xl text-black-dark leading-tight"> <span data-translate="error">Error</span> <span>1001</span> </h1> <span class="inline-block md:block heading-ray-id font-mono text-15 lg:text-sm lg:leading-relaxed">Ray ID: 7e2670336b1d04cd •</span> <span class="inline-block md:block heading-ray-id font-mono text-15 lg:text-sm lg:leading-relaxed">2023-07-06 08:22:09 UTC</span> <h2 class="text-gray-600 leading-1.3 text-3xl lg:text-2xl font-light">DNS resolution error</h2> </header>
<section class="w-240 lg:w-full mx-auto mb-8 lg:px-8">
<div id="what-happened-section" class="w-1/2 md:w-full">
<h2 class="text-3xl leading-tight font-normal mb-4 text-black-dark antialiased" data-translate="what_happened">What happened?</h2>
<p>You've requested a page on a website (gpt.free.lsdev.me) that is on the <a href="https://www.cloudflare.com/5xx-error-landing/" target="_blank">Cloudflare</a> network. Cloudflare is currently unable to resolve your requested domain (gpt.free.lsdev.me). There are two potential causes of this:</p>
<ul class="ml-10 mt-6 text-15 text-black-dark antialiased leading-normal">
<li class="mb-4"><strong class="font-semibold">Most likely:</strong> if the owner just signed up for Cloudflare it can take a few minutes for the website's information to be distributed to our global network.</li>
<li><strong>Less likely:</strong> something is wrong with this site's configuration. Usually this happens when accounts have been signed up with a partner organization (e.g., a hosting provider) and the provider's DNS fails.</li>
</ul>
</div>
</section>
<div class="feedback-hidden py-8 text-center" id="error-feedback">
<div id="error-feedback-survey" class="footer-line-wrapper">
Was this page helpful?
<button class="border border-solid bg-white cf-button cursor-pointer ml-4 px-4 py-2 rounded" id="feedback-button-yes" type="button">Yes</button>
<button class="border border-solid bg-white cf-button cursor-pointer ml-4 px-4 py-2 rounded" id="feedback-button-no" type="button">No</button>
</div>
<div class="feedback-success feedback-hidden" id="error-feedback-success">
Thank you for your feedback!
</div>
CopyCopy
</div>
<div class="cf-error-footer cf-wrapper w-240 lg:w-full py-10 sm:py-4 sm:px-8 mx-auto text-center sm:text-left border-solid border-0 border-t border-gray-300">
CopyCopy
<p class="text-13"> <span class="cf-footer-item sm:block sm:mb-1">Cloudflare Ray ID: <strong class="font-semibold">7e2670336b1d04cd</strong></span> <span class="cf-footer-separator sm:hidden">•</span> <span id="cf-footer-item-ip" class="cf-footer-item hidden sm:block sm:mb-1"> Your IP: <button type="button" id="cf-footer-ip-reveal" class="cf-footer-ip-reveal-btn">Click to reveal</button> <span class="hidden" id="cf-footer-ip"></span> <span class="cf-footer-separator sm:hidden">•</span> </span> <span class="cf-footer-item sm:block sm:mb-1"><span>Performance & security by</span> <a rel="noopener noreferrer" href="https://www.cloudflare.com/5xx-error-landing" id="brand_link" target="_blank">Cloudflare</a></span>
</p> <script>(function(){function d(){var b=a.getElementById("cf-footer-item-ip"),c=a.getElementById("cf-footer-ip-reveal");b&&"classList"in b&&(b.classList.remove("hidden"),c.addEventListener("click",function(){c.classList.add("hidden");a.getElementById("cf-footer-ip").classList.remove("hidden")}))}var a=document;document.addEventListener&&a.addEventListener("DOMContentLoaded",d)})();</script> </div><!-- /.error-footer -->
</div><!-- /#cf-error-details -->
CopyCopy
</div><!-- /#cf-wrapper -->
<script> window._cf_translation = {};
</script>
</body> </html>
<!doctype html> <title>500 Internal Server Error</title>
The server encountered an internal error and was unable to complete your request. Either the server is overloaded or there is an error in the application.
我正常启动后,在浏览器中访问一直显示超时,我已经开了代理
TLS/SSL connection has been closed (EOF) (_ssl.c:1131)
<traceback object at 0x0000018788A16740>
How do you enable the Jailbreak functionality?
getting the usual.. "I'm sorry, but I cannot provide that information.. "
Great project!
synology docker Run appears{"_action":"_ask","error":"an error occurred [Errno -3] Temporary failure in name resolution","success":false},how does synology docker enable automatic proxy?
What would be the easiest way to deploy to Netlify or Vercel?
Issue: Unable to Start Docker Image
Description:
I attempted to run a Docker image on a Debian 11 host using the KVM architecture from BandwagonHost. However, I encountered an issue with the startup process. Here are the relevant details:
Steps to Reproduce:
docker run -p 1338:1338 ramonvc/freegpt-webui
Problem Description:
The image fails to start, appearing to get stuck during the startup process. After attempting to start it, I pressed Ctrl+C to terminate the command and received the following error message:
2023-07-06T13:09:23Z
Traceback (most recent call last):
File "/app/./run.py", line 40, in <module>
Running on http://127.0.0.1:1338
Running on http://172.17.0.2:1338
server.serve_forever()
File "/root/.local/lib/python3.10/site-packages/gevent/baseserver.py", line 400, in serve_forever
self._stop_event.wait()
File "src/gevent/event.py", line 163, in gevent._gevent_cevent.Event.wait
File "src/gevent/_abstract_linkable.py", line 521, in gevent._gevent_c_abstract_linkable.AbstractLinkable._wait
File "src/gevent/_abstract_linkable.py", line 487, in gevent._gevent_c_abstract_linkable.AbstractLinkable._wait_core
File "src/gevent/_abstract_linkable.py", line 490, in gevent._gevent_c_abstract_linkable.AbstractLinkable._wait_core
File "src/gevent/_abstract_linkable.py", line 442, in gevent._gevent_c_abstract_linkable.AbstractLinkable._AbstractLinkable__wait_to_be_notified
File "src/gevent/_abstract_linkable.py", line 451, in gevent._gevent_c_abstract_linkable.AbstractLinkable._switch_to_hub
File "src/gevent/_greenlet_primitives.py", line 61, in gevent._gevent_c_greenlet_primitives.SwitchOutGreenletWithLoop.switch
File "src/gevent/_greenlet_primitives.py", line 65, in gevent._gevent_c_greenlet_primitives.SwitchOutGreenletWithLoop.switch
File "src/gevent/_gevent_c_greenlet_primitives.pxd", line 35, in gevent._gevent_c_greenlet_primitives._greenlet_switch
Expected Result:
I expected the image to start successfully and be accessible through port 1338 on the host.
Additional Information:
Thank you for your assistance!
Hi there,
This command not worked on arm64, do you have a plan to support it?
docker run -p 1338:1338 ramonvc/freegpt-webui
Error:
WARNING: The requested image's platform (linux/amd64) does not match the detected host platform (linux/arm64/v8) and no specific platform was requested
Platform:
Oracle Cloud Ubuntu 22.04 Arm 64
uname -a
Linux instance-20220508-1209-arm1 5.15.0-1034-oracle #40-Ubuntu SMP Wed Apr 19 16:10:04 UTC 2023 aarch64 aarch64 aarch64 GNU/Linux
Hey greetings,
You have made an awesome code.
I want to know about using the web access option.
I also want to know about GPT-4 which is under maintenance.
"POST /backend-api/v2/conversation HTTP/1.1" 400 -
At first, the app was working properly with 3.5 and any "mode" (4 is in maintenance).
However, now when I send any query to the chat in any mode, I get the 500 code back as the answer after some time.
I deployed it in docker on mac os with m1 chip.
Here is the answer I get.
<!doctype html> <html lang=en> <title>500 Internal Server Error</title> <h1>Internal Server Error</h1> <p>The server encountered an internal error and was unable to complete your request. Either the server is overloaded or there is an error in the application.</p>
Is this a local problem?
If yes, how can I solve it?
The server encountered an internal error and was unable to complete your request. Either the server is overloaded or there is an error in the application.
I have installed it using Portainer. I can access webui, the model is not responding to my queries
Could you please take a look the below logs and suggest?
https://pastebin.com/RMPNrPFh
docker image version: ecc12f173ca4
error: {"_action":"_ask","error":"an error occurred [Errno 99] Cannot assign requested address","success":false}
how to resolve it ?
logs
Accessing the address(http://127.0.0.1:1338) is ok, but receiving message is fail!
sorry,How to solve it?
{"_action":"_ask","error":"an error occurred [Errno 101] Network is unreachable","success":false}
Can you add the proxy address in config.json? Because the automatic proxy acquisition function cannot be used, it is hoped that the manual proxy address can be configured in config.json
Why do I click the send button and nothing happens?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.