返回提交历史
Modified
README.md
+48
-41
Modified
docs/client.md
+33
-8
Added
docs/guides/phone.jpeg
+0
-0
Added
docs/guides/phone.md
+50
-0
Added
docs/guides/phone.png
+0
-0
Added
docs/guides/phone2.jpeg
+0
-0
Added
docs/waterfall.jpeg
+0
-0
Modified
etc/tool/readme_table.py
+5
-3
Modified
g4f/Provider/FreeChatgpt.py
+11
-28
Modified
g4f/Provider/GeminiProChat.py
+0
-1
Modified
g4f/models.py
+5
-5
XFEstudio/gpt4free
Improve readme, add smartphone guide
79535603
代码差异
11 个文件
+152
-86
@@ -19,10 +19,10 @@ pip install -U g4f
19
19
docker pull hlohaus789/g4f
20
20
```
21
21
22
## 🆕 What's New
22
## 🆕 What's New 🚀
23
- How do I use my smartphone📱 to run g4f? [/docs/guides/phone](/docs/guides/phone.md)
23
24
- Join our Telegram Channel: [t.me/g4f_channel](https://telegram.me/g4f_channel)
24
25
- Join our Discord Group: [discord.gg/XfybzPXPH5](https://discord.gg/XfybzPXPH5)
25
- Explore the g4f Documentation (unfinished): [g4f.mintlify.app](https://g4f.mintlify.app) | Contribute to the docs via: [github.com/xtekky/gpt4free-docs](https://github.com/xtekky/gpt4free-docs)
26
26
27
27
## Site Takedown
28
28
Is your site on this repository and you want to take it down ? email takedown@g4f.ai with proof it is yours and it will be removed as fast as possible. - to prevent reproduction please secure your api ; )
@@ -34,13 +34,13 @@ You can always leave some feedback here: https://forms.gle/FeWV9RLEedfdkmFN6
34
34
As per the survey, here is a list of improvements to come
35
35
- [x] update the repository to include the new openai library syntax (ex: `Openai()` class) | completed, use `g4f.client.Client`
36
36
- [ ] golang implementation
37
- [ ] Improve Documentation (on g4f.mintlify.app) & Do video tutorials
38
- [ ] Improve the provider status list & updates
37
- [ ] 🚧 Improve Documentation (in /docs & Guides, Howtos, & Do video tutorials
38
- [x] Improve the provider status list & updates
39
39
- [ ] Tutorials on how to reverse sites to write your own wrapper (PoC only ofc)
40
40
- [ ] Improve the Bing wrapper. (might write a new wrapper in golang as it is very fast)
41
41
- [ ] Write a standard provider performance test to improve the stability
42
42
- [ ] Potential support and development of local models
43
- [ ] improve compatibility and error handling
43
- [ ] 🚧 improve compatibility and error handling
44
44
45
45
## 📚 Table of Contents
46
46
@@ -49,22 +49,17 @@ As per the survey, here is a list of improvements to come
49
49
- [🛠️ Getting Started](#-getting-started)
50
50
+ [Docker container](#docker-container)
51
51
- [Quick start](#quick-start)
52
+ [Use python package](#use-python-package)
52
+ [Use python](#use-python)
53
53
- [Prerequisites](#prerequisites)
54
- [Install using pypi](#install-using-pypi)
55
+ [Docker for Developers](#docker-for-developers)
54
- [Install using PyPI package:](#install-using-pypi-package-)
55
- [Install from source:](#install-from-source-)
56
- [Install using Docker:](#install-using-docker-)
56
57
- [💡 Usage](#-usage)
57
58
* [The Web UI](#the-web-ui)
58
* [The `g4f` Package](#the-g4f-package)
59
+ [ChatCompletion](#chatcompletion)
60
- [Completion](#completion)
61
- [Providers](#providers)
62
- [Using Browser](#using-browser)
63
- [Async Support](#async-support)
64
- [Proxy and Timeout Support](#proxy-and-timeout-support)
65
* [Interference openai-proxy API](#interference-openai-proxy-api-use-with-openai-python-package-)
66
+ [Run interference API from PyPi package](#run-interference-api-from-pypi-package)
67
+ [Run interference API from repo](#run-interference-api-from-repo)
59
* [Text Generation](#text-generation)
60
* [Image Generation](#text-generation)
61
* [Interference API](#interference-api)
62
* [Configuration](#configuration)
68
63
- [🚀 Providers and Models](#-providers-and-models)
69
64
* [GPT-4](#gpt-4)
70
65
* [GPT-3.5](#gpt-35)
@@ -96,6 +91,11 @@ docker run -p 8080:8080 -p 1337:1337 -p 7900:7900 --shm-size="2g" hlohaus789/g4f
96
91
or set the api base in your client to: [http://localhost:1337/v1](http://localhost:1337/v1)
97
92
4. (Optional) If you need to log in to a provider, you can view the desktop from the container here: http://localhost:7900/?autoconnect=1&resize=scale&password=secret.
98
93
94
##### Use your smartphone:
95
96
Run the Web UI on Your Smartphone:
97
- [/docs/guides/phone](/docs/guides/phone.md)
98
99
99
#### Use python
100
100
101
101
##### Prerequisites:
@@ -109,18 +109,19 @@ or set the api base in your client to: [http://localhost:1337/v1](http://localho
109
109
pip install -U g4f[all]
110
110
```
111
111
112
Or use partial requirements.
113
114
See: [/docs/requirements](/docs/requirements.md)
112
How do I install only parts or do disable parts?
113
Use partial requirements: [/docs/requirements](/docs/requirements.md)
115
114
116
##### Install from source using git:
115
##### Install from source:
117
116
118
See: [/docs/git](/docs/git.md)
117
How do I load the project using git and installing the project requirements?
118
Read this tutorial and follow it step by step: [/docs/git](/docs/git.md)
119
119
120
120
121
##### Install using Docker for Developers:
121
##### Install using Docker:
122
122
123
See: [/docs/docker](/docs/docker.md)
123
How do I build and run composer image from source?
124
Use docker-compose: [/docs/docker](/docs/docker.md)
124
125
125
126
126
127
## 💡 Usage
@@ -139,6 +140,10 @@ response = client.chat.completions.create(
139
140
print(response.choices[0].message.content)
140
141
```
141
142
143
```
144
Hello! How can I assist you today?
145
```
146
142
147
#### Image Generation
143
148
144
149
```python
@@ -159,8 +164,8 @@ image_url = response.data[0].url
159
164
160
165
**See also:**
161
166
162
- Documentation for the new Client: [/docs/client](/docs/client.md)
163
- Documentation for the leagcy API: [docs/leagcy](/docs/leagcy.md)
167
- Documentation for the new Client API: [/docs/client](/docs/client.md)
168
- Documentation for the leagcy API: [/docs/leagcy](/docs/leagcy.md)
164
169
165
170
166
171
#### Web UI
@@ -228,11 +233,10 @@ set G4F_PROXY=http://host:port
228
233
| Website | Provider | GPT-3.5 | GPT-4 | Stream | Status | Auth |
229
234
| ------ | ------- | ------- | ----- | ------ | ------ | ---- |
230
235
| [bing.com](https://bing.com/chat) | `g4f.Provider.Bing` | ❌ | ✔️ | ✔️ |  | ❌ |
231
| [free.chatgpt.org.uk](https://free.chatgpt.org.uk) | `g4f.Provider.FreeChatgpt` | ✔️ | ✔️ | ✔️ |  | ❌ |
232
236
| [liaobots.site](https://liaobots.site) | `g4f.Provider.Liaobots` | ✔️ | ✔️ | ✔️ |  | ❌ |
233
| [chat.openai.com](https://chat.openai.com) | `g4f.Provider.OpenaiChat` | ✔️ | ✔️ | ✔️ |  | ✔️ |
237
| [chat.openai.com](https://chat.openai.com) | `g4f.Provider.OpenaiChat` | ✔️ | ✔️ | ✔️ |  | ✔️ |
234
238
| [raycast.com](https://raycast.com) | `g4f.Provider.Raycast` | ✔️ | ✔️ | ✔️ |  | ✔️ |
235
| [beta.theb.ai](https://beta.theb.ai) | `g4f.Provider.Theb` | ✔️ | ✔️ | ✔️ |  | ❌ |
239
| [you.com](https://you.com) | `g4f.Provider.You` | ✔️ | ✔️ | ✔️ |  | ❌ |
236
240
| [chat.geekgpt.org](https://chat.geekgpt.org) | `g4f.Provider.GeekGpt` | ✔️ | ✔️ | ✔️ |  | ❌ |
237
241
238
242
### GPT-3.5
@@ -242,14 +246,13 @@ set G4F_PROXY=http://host:port
242
246
| [chat3.aiyunos.top](https://chat3.aiyunos.top/) | `g4f.Provider.AItianhuSpace` | ✔️ | ❌ | ✔️ |  | ❌ |
243
247
| [aichatonline.org](https://aichatonline.org) | `g4f.Provider.AiChatOnline` | ✔️ | ❌ | ✔️ |  | ❌ |
244
248
| [openchat.team](https://openchat.team) | `g4f.Provider.Aura` | ✔️ | ❌ | ✔️ |  | ❌ |
245
| [chatbase.co](https://www.chatbase.co) | `g4f.Provider.ChatBase` | ✔️ | ❌ | ✔️ |  | ❌ |
249
| [chatbase.co](https://www.chatbase.co) | `g4f.Provider.ChatBase` | ✔️ | ❌ | ✔️ |  | ❌ |
246
250
| [chatforai.store](https://chatforai.store) | `g4f.Provider.ChatForAi` | ✔️ | ❌ | ✔️ |  | ❌ |
247
251
| [chatgpt.ai](https://chatgpt.ai) | `g4f.Provider.ChatgptAi` | ✔️ | ❌ | ✔️ |  | ❌ |
248
252
| [chat.chatgptdemo.net](https://chat.chatgptdemo.net) | `g4f.Provider.ChatgptDemo` | ✔️ | ❌ | ✔️ |  | ❌ |
249
253
| [chatgpt-free.cc](https://www.chatgpt-free.cc) | `g4f.Provider.ChatgptNext` | ✔️ | ❌ | ✔️ |  | ❌ |
250
254
| [chat.3211000.xyz](https://chat.3211000.xyz) | `g4f.Provider.Chatxyz` | ✔️ | ❌ | ✔️ |  | ❌ |
251
255
| [gptalk.net](https://gptalk.net) | `g4f.Provider.GPTalk` | ✔️ | ❌ | ✔️ |  | ❌ |
252
| [geminiprochat.com](https://geminiprochat.com) | `g4f.Provider.GeminiProChat` | ✔️ | ❌ | ✔️ |  | ❌ |
253
256
| [gpt6.ai](https://gpt6.ai) | `g4f.Provider.Gpt6` | ✔️ | ❌ | ✔️ |  | ❌ |
254
257
| [gptchatly.com](https://gptchatly.com) | `g4f.Provider.GptChatly` | ✔️ | ❌ | ❌ |  | ❌ |
255
258
| [ai18.gptforlove.com](https://ai18.gptforlove.com) | `g4f.Provider.GptForLove` | ✔️ | ❌ | ✔️ |  | ❌ |
@@ -261,7 +264,6 @@ set G4F_PROXY=http://host:port
261
264
| [perplexity.ai](https://www.perplexity.ai) | `g4f.Provider.PerplexityAi` | ✔️ | ❌ | ✔️ |  | ❌ |
262
265
| [poe.com](https://poe.com) | `g4f.Provider.Poe` | ✔️ | ❌ | ✔️ |  | ✔️ |
263
266
| [talkai.info](https://talkai.info) | `g4f.Provider.TalkAi` | ✔️ | ❌ | ✔️ |  | ❌ |
264
| [you.com](https://you.com) | `g4f.Provider.You` | ✔️ | ❌ | ✔️ |  | ❌ |
265
267
| [aitianhu.com](https://www.aitianhu.com) | `g4f.Provider.AItianhu` | ✔️ | ❌ | ✔️ |  | ❌ |
266
268
| [e.aiask.me](https://e.aiask.me) | `g4f.Provider.AiAsk` | ✔️ | ❌ | ✔️ |  | ❌ |
267
269
| [chatgpt.bestim.org](https://chatgpt.bestim.org) | `g4f.Provider.Bestim` | ✔️ | ❌ | ✔️ |  | ❌ |
@@ -284,12 +286,16 @@ set G4F_PROXY=http://host:port
284
286
| ------ | ------- | ------- | ----- | ------ | ------ | ---- |
285
287
| [bard.google.com](https://bard.google.com) | `g4f.Provider.Bard` | ❌ | ❌ | ❌ |  | ✔️ |
286
288
| [deepinfra.com](https://deepinfra.com) | `g4f.Provider.DeepInfra` | ❌ | ❌ | ✔️ |  | ❌ |
287
| [gemini.google.com](https://gemini.google.com) | `g4f.Provider.Gemini` | ❌ | ❌ | ❌ |  | ✔️ |
288
| [huggingface.co](https://huggingface.co/chat) | `g4f.Provider.HuggingChat` | ❌ | ❌ | ✔️ |  | ❌ |
289
| [gemini.google.com](https://gemini.google.com) | `g4f.Provider.Gemini` | ❌ | ❌ | ✔️ |  | ✔️ |
290
| [ai.google.dev](https://ai.google.dev) | `g4f.Provider.GeminiPro` | ❌ | ❌ | ✔️ |  | ❌ |
291
| [gemini-chatbot-sigma.vercel.app](https://gemini-chatbot-sigma.vercel.app) | `g4f.Provider.GeminiProChat` | ✔️ | ❌ | ✔️ |  | ❌ |
292
| [huggingface.co](https://huggingface.co/chat) | `g4f.Provider.HuggingChat` | ❌ | ❌ | ✔️ |  | ❌ |
289
293
| [llama2.ai](https://www.llama2.ai) | `g4f.Provider.Llama2` | ❌ | ❌ | ✔️ |  | ❌ |
290
294
| [labs.perplexity.ai](https://labs.perplexity.ai) | `g4f.Provider.PerplexityLabs` | ❌ | ❌ | ✔️ |  | ❌ |
291
| [phind.com](https://www.phind.com) | `g4f.Provider.Phind` | ❌ | ❌ | ✔️ |  | ❌ |
292
| [pi.ai](https://pi.ai/talk) | `g4f.Provider.Pi` | ❌ | ❌ | ✔️ |  | ❌ |
295
| [phind.com](https://www.phind.com) | `g4f.Provider.Phind` | ❌ | ❌ | ✔️ |  | ❌ |
296
| [pi.ai](https://pi.ai/talk) | `g4f.Provider.Pi` | ❌ | ❌ | ✔️ |  | ❌ |
297
| [beta.theb.ai](https://beta.theb.ai) | `g4f.Provider.Theb` | ✔️ | ✔️ | ✔️ |  | ❌ |
298
| [free.chatgpt.org.uk](https://free.chatgpt.org.uk) | `g4f.Provider.FreeChatgpt` | ✔️ | ✔️ | ✔️ |  | ❌ |
293
299
| [theb.ai](https://theb.ai) | `g4f.Provider.ThebApi` | ❌ | ❌ | ❌ |  | ✔️ |
294
300
| [open-assistant.io](https://open-assistant.io/chat) | `g4f.Provider.OpenAssistant` | ❌ | ❌ | ✔️ |  | ✔️ |
295
301
@@ -300,10 +306,11 @@ set G4F_PROXY=http://host:port
300
306
| gpt-3.5-turbo | OpenAI | 5+ Providers | [openai.com](https://openai.com/) |
301
307
| gpt-4 | OpenAI | 2+ Providers | [openai.com](https://openai.com/) |
302
308
| gpt-4-turbo | OpenAI | g4f.Provider.Bing | [openai.com](https://openai.com/) |
303
| Llama-2-7b-chat-hf | Huggingface | 2+ Providers | [huggingface.co](https://huggingface.co/) |
304
| Llama-2-13b-chat-hf | Huggingface | 2+ Providers | [huggingface.co](https://huggingface.co/) |
305
| Llama-2-70b-chat-hf | Huggingface | 4+ Providers | [huggingface.co](https://huggingface.co/) |
306
| CodeLlama-34b-Instruct-hf | Huggingface | 3+ Providers | [huggingface.co](https://huggingface.co/) |
309
| Llama-2-7b-chat-hf | Meta | 2+ Providers | [llama.meta.com](https://llama.meta.com/) |
310
| Llama-2-13b-chat-hf | Meta | 2+ Providers | [llama.meta.com](https://llama.meta.com/) |
311
| Llama-2-70b-chat-hf | Meta | 4+ Providers | [llama.meta.com](https://llama.meta.com/) |
312
| CodeLlama-34b-Instruct-hf | Meta | 3+ Providers | [llama.meta.com](https://llama.meta.com/) |
313
| CodeLlama-70b-Instruct-hf | Meta | g4f.Provider.DeepInfra | [llama.meta.com](https://llama.meta.com/) |
307
314
| Mixtral-8x7B-Instruct-v0.1 | Huggingface | 3+ Providers | [huggingface.co](https://huggingface.co/) |
308
315
| Mistral-7B-Instruct-v0.1 | Huggingface | 3+ Providers | [huggingface.co](https://huggingface.co/) |
309
316
| dolphin-2.6-mixtral-8x7b | Huggingface | g4f.Provider.DeepInfra | [huggingface.co](https://huggingface.co/) |
@@ -1,4 +1,4 @@
1
### G4F - Client API (Beta Version)
1
### G4F - Client API
2
2
3
3
#### Introduction
4
4
@@ -39,7 +39,7 @@ client = Client(
39
39
40
40
## Configuration
41
41
42
You can set an "api_key" for your provider in client.
42
You can set an "api_key" for your provider in the client.
43
43
And you also have the option to define a proxy for all outgoing requests:
44
44
45
45
```python
@@ -108,13 +108,35 @@ response = client.images.create_variation(
108
108
109
109
image_url = response.data[0].url
110
110
```
111
112
#### Visual Examples
113
114
111
Original / Variant:
115
112
116
113
[](/docs/client.md) [](/docs/client.md)
117
114
115
#### Use a list of providers with RetryProvider
116
117
```python
118
from g4f.client import Client
119
from g4f.Provider import RetryProvider, Phind, FreeChatgpt, Liaobots
120
121
import g4f.debug
122
g4f.debug.logging = True
123
124
client = Client(
125
provider=RetryProvider([Phind, FreeChatgpt, Liaobots], shuffle=False)
126
)
127
response = client.chat.completions.create(
128
model="",
129
messages=[{"role": "user", "content": "Hello"}],
130
)
131
print(response.choices[0].message.content)
132
```
133
134
```
135
Using RetryProvider provider
136
Using Phind provider
137
How can I assist you today?
138
```
139
118
140
#### Advanced example using GeminiProVision
119
141
120
142
```python
@@ -128,13 +150,16 @@ client = Client(
128
150
response = client.chat.completions.create(
129
151
model="gemini-pro-vision",
130
152
messages=[{"role": "user", "content": "What are on this image?"}],
131
image=open("docs/cat.jpeg", "rb")
153
image=open("docs/waterfall.jpeg", "rb")
132
154
)
133
155
print(response.choices[0].message.content)
134
156
```
135
**Question:** What are on this image?
157
158
```
159
User: What are on this image?
160
```
136
161
```
137
A cat is sitting on a window sill looking at a bird outside the window.
162
Bot: There is a waterfall in the middle of a jungle. There is a rainbow over...
138
163
```
139
164
140
165
[Return to Home](/)
二进制文件已变更，无法进行逐行预览。
@@ -0,0 +1,50 @@
1
### Guide: Running the G4F GUI on Your Smartphone
2
3
Running Python applications on your smartphone is possible with specialized apps like Pydroid. This tutorial will walk you through the process using an Android smartphone with Pydroid. Note that the steps may vary slightly for iPhone users due to differences in app names and ownership.
4
5
<p align="center">
6
On the first screenshot is <strong>Pydroid</strong> and on the second is the <strong>Web UI</strong> in a browser
7
</p>
8
9
<p align="center">
10
<img src="/docs/guides/phone.png" />
11
<img src="/docs/guides/phone2.jpeg" />
12
</p>
13
14
1. **Install Pydroid from the Google Play Store:**
15
- Navigate to the Google Play Store and search for "Pydroid 3 - IDE for Python 3" or use the following link: [Pydroid 3 - IDE for Python 3](https://play.google.com/store/apps/details/Pydroid_3_IDE_for_Python_3).
16
17
2. **Install the Pydroid Repository Plugin:**
18
- To enhance functionality, install the Pydroid repository plugin. Find it on the Google Play Store or use this link: [Pydroid Repository Plugin](https://play.google.com/store/apps/details?id=ru.iiec.pydroid3.quickinstallrepo).
19
20
3. **Adjust App Settings:**
21
- In the app settings for Pydroid, disable power-saving mode and ensure that the option to pause when not in use is also disabled. This ensures uninterrupted operation of your Python scripts.
22
23
4. **Install Required Packages:**
24
- Open Pip within the Pydroid app and install the necessary packages by executing the following commands:
25
```
26
pip install g4f flask pillow beautifulsoup4
27
```
28
29
5. **Create a New Python Script:**
30
- Within Pydroid, create a new Python script and input the following content:
31
```python
32
from g4f import set_cookies
33
34
set_cookies(".bing.com", {
35
"_U": "cookie value"
36
})
37
38
from g4f.gui import run_gui
39
40
run_gui("0.0.0.0", 8080, debug=True)
41
```
42
Replace `"cookie value"` with your actual cookie value from Bing if you intend to create images using Bing.
43
44
6. **Execute the Script:**
45
- Run the script by clicking on the play button or selecting the option to execute it.
46
47
7. **Access the GUI:**
48
- Wait for the server to start, and once it's running, open the GUI using the URL provided in the output. [http://localhost:8080/chat/](http://localhost:8080/chat/)
49
50
By following these steps, you can successfully run the G4F GUI on your smartphone using Pydroid, allowing you to create and interact with graphical interfaces directly from your device.
二进制文件已变更，无法进行逐行预览。
二进制文件已变更，无法进行逐行预览。
二进制文件已变更，无法进行逐行预览。
@@ -87,7 +87,8 @@ def print_models():
87
87
"openai": "OpenAI",
88
88
"huggingface": "Huggingface",
89
89
"anthropic": "Anthropic",
90
"inflection": "Inflection"
90
"inflection": "Inflection",
91
"meta": "Meta"
91
92
}
92
93
provider_urls = {
93
94
"google": "https://gemini.google.com/",
@@ -95,6 +96,7 @@ def print_models():
95
96
"huggingface": "https://huggingface.co/",
96
97
"anthropic": "https://www.anthropic.com/",
97
98
"inflection": "https://inflection.ai/",
99
"meta": "https://llama.meta.com/"
98
100
}
99
101
100
102
lines = [
@@ -120,6 +122,6 @@ def print_models():
120
122
print("\n".join(lines))
121
123
122
124
if __name__ == "__main__":
123
#print_providers()
124
#print("\n", "-" * 50, "\n")
125
print_providers()
126
print("\n", "-" * 50, "\n")
125
127
print_models()
@@ -4,24 +4,13 @@ import json, random
4
4
from aiohttp import ClientSession
5
5
6
6
from ..typing import AsyncResult, Messages
7
from .base_provider import AsyncGeneratorProvider
7
from .base_provider import AsyncGeneratorProvider, ProviderModelMixin
8
8
9
models = {
10
"claude-v2": "claude-2.0",
11
"claude-v2.1":"claude-2.1",
12
"gemini-pro": "google-gemini-pro"
13
}
14
urls = [
15
"https://free.chatgpt.org.uk",
16
"https://ai.chatgpt.org.uk"
17
]
18
19
class FreeChatgpt(AsyncGeneratorProvider):
9
class FreeChatgpt(AsyncGeneratorProvider, ProviderModelMixin):
20
10
url = "https://free.chatgpt.org.uk"
21
11
working = True
22
supports_gpt_35_turbo = True
23
supports_gpt_4 = True
24
12
supports_message_history = True
13
default_model = "google-gemini-pro"
25
14
26
15
@classmethod
27
16
async def create_async_generator(
@@ -31,11 +20,6 @@ class FreeChatgpt(AsyncGeneratorProvider):
31
20
proxy: str = None,
32
21
**kwargs
33
22
) -> AsyncResult:
34
if model in models:
35
model = models[model]
36
elif not model:
37
model = "gpt-3.5-turbo"
38
url = random.choice(urls)
39
23
headers = {
40
24
"Accept": "application/json, text/event-stream",
41
25
"Content-Type":"application/json",
@@ -51,16 +35,15 @@ class FreeChatgpt(AsyncGeneratorProvider):
51
35
}
52
36
async with ClientSession(headers=headers) as session:
53
37
data = {
54
"messages":messages,
55
"stream":True,
56
"model":model,
57
"temperature":0.5,
58
"presence_penalty":0,
59
"frequency_penalty":0,
60
"top_p":1,
61
**kwargs
38
"messages": messages,
39
"stream": True,
40
"model": cls.get_model(""),
41
"temperature": kwargs.get("temperature", 0.5),
42
"presence_penalty": kwargs.get("presence_penalty", 0),
43
"frequency_penalty": kwargs.get("frequency_penalty", 0),
44
"top_p": kwargs.get("top_p", 1)
62
45
}
63
async with session.post(f'{url}/api/openai/v1/chat/completions', json=data, proxy=proxy) as response:
46
async with session.post(f'{cls.url}/api/openai/v1/chat/completions', json=data, proxy=proxy) as response:
64
47
response.raise_for_status()
65
48
started = False
66
49
async for line in response.content:
@@ -11,7 +11,6 @@ from .base_provider import AsyncGeneratorProvider
11
11
class GeminiProChat(AsyncGeneratorProvider):
12
12
url = "https://gemini-chatbot-sigma.vercel.app"
13
13
working = True
14
supports_gpt_35_turbo = True
15
14
16
15
@classmethod
17
16
async def create_async_generator(
@@ -99,31 +99,31 @@ gpt_4_turbo = Model(
99
99
100
100
llama2_7b = Model(
101
101
name = "meta-llama/Llama-2-7b-chat-hf",
102
base_provider = 'huggingface',
102
base_provider = 'meta',
103
103
best_provider = RetryProvider([Llama2, DeepInfra])
104
104
)
105
105
106
106
llama2_13b = Model(
107
107
name = "meta-llama/Llama-2-13b-chat-hf",
108
base_provider = 'huggingface',
108
base_provider = 'meta',
109
109
best_provider = RetryProvider([Llama2, DeepInfra])
110
110
)
111
111
112
112
llama2_70b = Model(
113
113
name = "meta-llama/Llama-2-70b-chat-hf",
114
base_provider = "huggingface",
114
base_provider = "meta",
115
115
best_provider = RetryProvider([Llama2, DeepInfra, HuggingChat, PerplexityLabs])
116
116
)
117
117
118
118
codellama_34b_instruct = Model(
119
119
name = "codellama/CodeLlama-34b-Instruct-hf",
120
base_provider = "huggingface",
120
base_provider = "meta",
121
121
best_provider = RetryProvider([HuggingChat, PerplexityLabs, DeepInfra])
122
122
)
123
123
124
124
codellama_70b_instruct = Model(
125
125
name = "codellama/CodeLlama-70b-Instruct-hf",
126
base_provider = "huggingface",
126
base_provider = "meta",
127
127
best_provider = DeepInfra
128
128
)
129
129