No project description provided
Project description
Juchats API wrapper
juchats
lib is a Python library designed for interacting with the Juchats API, enabling seamless integration of chat functionalities into your applications. By utilizing this library, developers can leverage the power of advanced models like GPT-4, Claude Mezzo, and deepseek to perform various chat-related tasks.
Installation
pip3 install juchats
Usage
First, obtain your token from from Juchats official website, and place it into a .env
file.
JTOKEN=your_token
Basic Chat Interaction
This example demonstrates a simple chat interaction where we ask the model to compare two floating-point numbers.
import os
from juchats.chat import Juchats
from dotenv import load_dotenv
import asyncio
load_dotenv()
async def api():
token = os.getenv('JTOKEN')
juchats = Juchats(token, model='deepseek-chat')
async with juchats:
await juchats.chat("3.11, 3.9 两个浮点数谁大?具体分析一下,给出你的原因", show_stream=True)
if __name__ == '__main__':
asyncio.run(api())
''' Output
3.11 大,因为 3.11 > 3.9
'''
Structured JSON output
This example demonstrates how to obtain structured JSON output from the chat API.
import os
from juchats.chat import Juchats
from dotenv import load_dotenv
import asyncio
load_dotenv()
async def api():
token = os.getenv('JTOKEN')
juchats = Juchats(token, model='deepseek-chat')
prompt = "每个月有多少天?以 JSON 格式给出答案,例如:{\"January\": 31, \"February\": 28, ...}"
async with juchats:
text = await juchats.chat(prompt)
print(text)
''' Output
```json
{
"January": 31,
"February": 28,
"March": 31,
"April": 30,
"May": 31,
"June": 30,
"July": 31,
"August": 31,
"September": 30,
"October": 31,
"November": 30,
"December": 31
}
'''
Available Models
By 2024-07-25, the available models (may be outdated) are:
Model ID | Backend Model Name | Front Model Name |
---|---|---|
5 | claude-3-haiku-20240307 | Claude Mezzo |
6 | claude-3-opus-20240229 | Claude3 Opus |
7 | mistralai/mixtral-8x22b-instruct | Mixtral Forte |
9 | gpt-4-turbo-2024-04-09 | GPT Mezzo |
10 | gpt-4-turbo-2024-04-09 | GPT Forte |
11 | dall-e-3 | DALL · E3 |
12 | meta-llama/llama-3-70b-instruct | Llama3 70B |
13 | google/gemini-pro-1.5 | Gemini 1.5 Pro |
14 | deepseek-chat | Deepseek |
15 | google/gemini-flash-1.5 | Gemini-flash |
16 | gpt-4o-2024-05-13 | GPT4o |
17 | claude-3-opus-20240229 | Claude3 Opus(100K) |
18 | Stable Image Ultra | Stable Diffusion 3 Ultra |
19 | claude-3-5-sonnet-20240620 | Claude 3.5 Sonnet |
20 | gpt-4o-mini-2024-07-18 | GPT4o-mini |
21 | meta-llama/llama-3.1-405b-instruct | Llama3.1 405B |
Get real time available models
Dynamically retrieve the latest available models from the Juchats API.
import os
from juchats.chat import Juchats
from dotenv import load_dotenv
import asyncio
load_dotenv()
token = os.getenv('JTOKEN')
juchats = Juchats(token, model='gpt-4o-2024-05-13')
print(
asyncio.run(juchats.get_models())
)
Note
- Streaming: Set
show_stream=True
to display the chat response in real-time. Useshow_stream=False
to disable it. - Model Selection: Specify the backend model name with the
model
parameter. Refer to the available models table above for options. - API Token: Obtain your token from Juchats and use it to authenticate requests.
- Rate Limiting: The API supports up to 3 queries per second (QPS). For higher limits, consider using the Deepseek API or OpenAI API.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file juchats-0.0.3.tar.gz
.
File metadata
- Download URL: juchats-0.0.3.tar.gz
- Upload date:
- Size: 5.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.8.3 CPython/3.9.18 Darwin/22.4.0
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 77eeab2324f4b5fb4ce0c4d481b95c42cd7afc6867e529444382aa16f591f8c1 |
|
MD5 | 678800866ce0dc13685eaddfc6606a7b |
|
BLAKE2b-256 | 8e5603dc019a6c1073507e6dd3cc774778889bc6fce18069043741b1f0d36e4b |
File details
Details for the file juchats-0.0.3-py3-none-any.whl
.
File metadata
- Download URL: juchats-0.0.3-py3-none-any.whl
- Upload date:
- Size: 7.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.8.3 CPython/3.9.18 Darwin/22.4.0
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9205df8063ebed7d244c1bf98ff7ee283ea1f2ed70efc4f644fe46b26988ffd5 |
|
MD5 | 92b92f469e581a92e2a51dfbb5362a91 |
|
BLAKE2b-256 | 9443d1c22b04c13f018e281b348a0488ac77f7207511eb2603d21c39c3a52f44 |