Python client for WeyCP API - Advanced AI chat completions service

These details have not been verified by PyPI

Project links

Project description

WeyCP Python Client# WeyCP Python Client# WeyCP Python Client# WeyCP Python Client# WeyCP Python Client

The official Python client for WeyCP API - Advanced AI chat completions service.

Features

🚀 Familiar API Interface - Easy-to-use chat completions API
🔄 Sync & Async support - Use synchronous or asynchronous clients
🛡️ Built-in error handling - Comprehensive exception handlingThe official Python client for WeyCP API - Advanced AI chat completions service.
📊 Usage tracking - Monitor token usage and costs
🎯 Type hints - Full type annotation support
⚡ High performance - Optimized for concurrent requests

Features Official Python client for WeyCP API - OpenAI-compatible chat completions using Ollama.

Installation

pip install weycop- 🚀 **Familiar API Interface** - Easy-to-use chat completions API

🔄 Sync & Async support - Use synchronous or asynchronous clients

Quick Start

🛡️ Built-in error handling - Comprehensive exception handlingThe official Python client for WeyCP API - Advanced AI chat completions service.

Synchronous Client

📊 Usage tracking - Monitor token usage and costs

from weycop import WeycopClient- 🎯 **Type hints** - Full type annotation support



# Initialize client- ⚡ **High performance** - Optimized for concurrent requests

client = WeycopClient(api_key="your-api-key")

## Features[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)## Installation

# Simple chat

response = client.chat(## Installation

    message="Hello, how are you?",

    model="llama3.2:3b",

    system_prompt="You are a helpful assistant"

)```bash

print(response)

pip install weycop- 🚀 **Familiar API Interface** - Easy-to-use chat completions API

# Advanced usage

completion = client.chat_completions_create(```

    model="llama3.2:3b",

    messages=[- 🔄 **Sync & Async support** - Use synchronous or asynchronous clients

        {"role": "system", "content": "You are a helpful assistant"},

        {"role": "user", "content": "Explain quantum computing"}## Quick Start

    ],

    temperature=0.7,- 🛡️ **Built-in error handling** - Comprehensive exception handlingThe official Python client for WeyCP API - OpenAI-compatible chat completions powered by Ollama.```bash

    max_tokens=500

)### Synchronous Client

print(completion.choices[0].message.content)

```- 📊 **Usage tracking** - Monitor token usage and costs



### Asynchronous Client```python



```pythonfrom weycop import WeycopClient- 🎯 **Type hints** - Full type annotation supportpip install weycop

import asyncio

from weycop import AsyncWeycopClient



async def main():# Initialize client- ⚡ **High performance** - Optimized for concurrent requests

    async with AsyncWeycopClient(api_key="your-api-key") as client:

        response = await client.chat(client = WeycopClient(api_key="your-api-key")

            message="What is machine learning?",

            model="llama3.1:8b-8k"## Features```

        )

        print(response)# Simple chat



asyncio.run(main())response = client.chat(## Installation

message="Hello, how are you?",

Supported Models

model="llama3.2:3b",

llama3.2:3b - Fast, lightweight model (4GB VRAM)
llama3.1:8b-8k - Advanced model with 8K context (8.5GB VRAM) system_prompt="You are a helpful assistant"

Error Handling)```bash

from weycop import WeycopClient, AuthenticationError, RateLimitError, APIError

pip install weycop- 🚀 **OpenAI-compatible API** - Drop-in replacement for OpenAI client## Quick Start

client = WeycopClient(api_key="your-key")

# Advanced usage

try:

    response = client.chat("Hello", model="llama3.2:3b")completion = client.chat_completions_create(```

except AuthenticationError:

    print("Invalid API key")    model="llama3.2:3b",

except RateLimitError:

    print("Rate limit exceeded")    messages=[- 🔄 **Sync & Async support** - Use synchronous or asynchronous clients

except APIError as e:

    print(f"API error: {e}")        {"role": "system", "content": "You are a helpful assistant"},

    {"role": "user", "content": "Explain quantum computing"}## Quick Start

Advanced Usage

],

Custom Parameters

temperature=0.7,- 🛡️ **Built-in error handling** - Comprehensive exception handling### Synchronous Usage

response = client.chat_completions_create(    max_tokens=500

    model="llama3.2:3b",

    messages=[{"role": "user", "content": "Write a short story"}],)### Synchronous Client

    temperature=0.8,

    max_tokens=1000,print(completion.choices[0].message.content)

    top_p=0.9,

    stop=["END", "###"]```- 📊 **Usage tracking** - Monitor token usage and costs

)

Health Check### Asynchronous Client```python

health = client.health_check()

print(f"Status: {health.status}")```pythonfrom weycop import WeycopClient- 🎯 **Type hints** - Full type annotation support```python

print(f"Available models: {len(health.ollama_models)}")

```import asyncio



## Examplesfrom weycop import AsyncWeycopClient



Check the `examples/` directory for more usage examples:

- `basic_usage.py` - Simple chat completions

- `error_handling.py` - Comprehensive error handlingasync def main():# Initialize client- ⚡ **High performance** - Optimized for concurrent requestsimport weycop



## Support    async with AsyncWeycopClient(api_key="your-api-key") as client:



- 📧 Email: [apps@weycop.com](mailto:apps@weycop.com)        response = await client.chat(client = WeycopClient(api_key="your-api-key")

- 🐛 Issues: [GitHub Issues](https://github.com/weycop/weycop-python/issues)

            message="What is machine learning?",

## License

            model="llama3.1:8b-8k"

MIT License - see [LICENSE](LICENSE) file for details.
        )

        print(response)# Simple chat



asyncio.run(main())response = client.chat(## Installation# Initialize client

message="Hello, how are you?",

Supported Models

model="llama3.2:3b",client = weycop.WeycopClient(api_key="your-api-key-here")

llama3.2:3b - Fast, lightweight model (4GB VRAM)
llama3.1:8b-8k - Advanced model with 8K context (8.5GB VRAM) system_prompt="You are a helpful assistant"

Error Handling)```bash

from weycop import WeycopClient, AuthenticationError, RateLimitError, APIError

pip install weycop# Simple chat

client = WeycopClient(api_key="your-key")

# Advanced usage

try:

    response = client.chat("Hello", model="llama3.2:3b")completion = client.chat_completions_create(```response = client.chat("Hello, how are you?")

except AuthenticationError:

    print("Invalid API key")    model="llama3.2:3b",

except RateLimitError:

    print("Rate limit exceeded")    messages=[print(response)

except APIError as e:

    print(f"API error: {e}")        {"role": "system", "content": "You are a helpful assistant"},

    {"role": "user", "content": "Explain quantum computing"}## Quick Start

Advanced Usage

],

Custom Parameters

temperature=0.7,# Advanced chat completion

response = client.chat_completions_create(    max_tokens=500

    model="llama3.2:3b",

    messages=[{"role": "user", "content": "Write a short story"}],)### Synchronous Clientfrom weycop import Message

    temperature=0.8,

    max_tokens=1000,print(completion.choices[0].message.content)

    top_p=0.9,

    stop=["END", "###"]```

)

Health Check### Asynchronous Client```pythoncompletion = client.chat_completions_create(

health = client.health_check()

print(f"Status: {health.status}")```pythonfrom weycop import WeycopClient    model="llama3.2:3b",

print(f"Available models: {len(health.ollama_models)}")

```import asyncio



## Examplesfrom weycop import AsyncWeycopClient    messages=[



Check the `examples/` directory for more usage examples:

- `basic_usage.py` - Simple chat completions

- `error_handling.py` - Comprehensive error handlingasync def main():# Initialize client        Message("system", "You are a helpful assistant."),



## API Documentation    async with AsyncWeycopClient(api_key="your-api-key") as client:



Visit [https://api.weycop.com/docs](https://api.weycop.com/docs) for complete API documentation.        response = await client.chat(client = WeycopClient(api_key="your-api-key")        Message("user", "Explain quantum computing in simple terms.")



## Support            message="What is machine learning?",



- 📧 Email: [apps@weycop.com](mailto:apps@weycop.com)            model="llama3.1:8b-8k"    ],

- 🐛 Issues: [GitHub Issues](https://github.com/weycop/weycop-python/issues)

- 📖 Docs: [https://docs.weycop.com](https://docs.weycop.com)        )



## License        print(response)# Simple chat    temperature=0.7,



MIT License - see [LICENSE](LICENSE) file for details.

asyncio.run(main())response = client.chat(    max_tokens=150

message="Hello, how are you?",)

Supported Models

model="llama3.2:3b",

llama3.2:3b - Fast, lightweight model (4GB VRAM)
llama3.1:8b-8k - Advanced model with 8K context (8.5GB VRAM) system_prompt="You are a helpful assistant"print(completion.choices[0].message.content)

Error Handling)print(f"Used {completion.usage.total_tokens} tokens")

pythonprint(response)

from weycop import WeycopClient, AuthenticationError, RateLimitError, APIError

client = WeycopClient(api_key="your-key")

Advanced usage### Asynchronous Usage

try:

response = client.chat("Hello", model="llama3.2:3b")completion = client.chat_completions_create(

except AuthenticationError:

print("Invalid API key")    model="llama3.2:3b",```python

except RateLimitError:

print("Rate limit exceeded")    messages=[import asyncio

except APIError as e:

print(f"API error: {e}")        {"role": "system", "content": "You are a helpful assistant"},import weycop


        {"role": "user", "content": "Explain quantum computing"}

## Advanced Usage

    ],async def main():

### Custom Parameters

    temperature=0.7,    async with weycop.AsyncWeycopClient(api_key="your-api-key-here") as client:

```python

response = client.chat_completions_create(    max_tokens=500        response = await client.chat("What's the weather like?")

    model="llama3.2:3b",

    messages=[{"role": "user", "content": "Write a short story"}],)        print(response)

    temperature=0.8,

    max_tokens=1000,print(completion.choices[0].message.content)

    top_p=0.9,

    stop=["END", "###"]```asyncio.run(main())

)

Health Check### Asynchronous Client

health = client.health_check()

print(f"Status: {health.status}")```python

print(f"Models: {len(health.ollama_models)}")

```import asyncio### Environment Variables



## Examplesfrom weycop import AsyncWeycopClient



Check the `examples/` directory for more usage examples:You can set your API key using environment variables:

- `basic_usage.py` - Simple chat completions

- `error_handling.py` - Comprehensive error handlingasync def main():



## API Documentation    async with AsyncWeycopClient(api_key="your-api-key") as client:```bash



Visit [https://api.weycop.com/docs](https://api.weycop.com/docs) for complete API documentation.        response = await client.chat(export WEYCOP_API_KEY="your-api-key-here"



## Support            message="What is machine learning?",export WEYCOP_BASE_URL="https://api.weycop.com"  # Optional



- 📧 Email: [dev@weycop.com](mailto:dev@weycop.com)            model="llama3.1:8b-8k"```

- 🐛 Issues: [GitHub Issues](https://github.com/weycop/weycop-python/issues)

- 📖 Docs: [https://docs.weycop.com](https://docs.weycop.com)        )



## License        print(response)### Client Configuration



MIT License - see [LICENSE](LICENSE) file for details.

asyncio.run(main())```python

```client = weycop.WeycopClient(

    api_key="your-api-key-here",

## Supported Models    base_url="https://api.weycop.com",  # Optional

    timeout=120.0  # Optional, request timeout in seconds

- `llama3.2:3b` - Fast, lightweight model (4GB VRAM))

- `llama3.1:8b-8k` - Advanced model with 8K context (8.5GB VRAM)```



## Error Handling## Available Models



```python- `llama3.2:3b` - Fast model for general chat and small tasks

from weycop import WeycopClient, AuthenticationError, RateLimitError, APIError- `llama3.1:8b` - More powerful model for complex reasoning and SQL tasks



client = WeycopClient(api_key="your-key")## API Reference



try:### WeycopClient Methods

    response = client.chat("Hello", model="llama3.2:3b")

except AuthenticationError:#### `chat_completions_create()`

    print("Invalid API key")

except RateLimitError:Create a chat completion with full control over parameters.

    print("Rate limit exceeded")

except APIError as e:```python

    print(f"API error: {e}")completion = client.chat_completions_create(

```    model="llama3.2:3b",

    messages=[Message("user", "Hello!")],

## Advanced Usage    temperature=0.7,        # Optional: 0-2, controls randomness

    top_p=0.9,             # Optional: 0-1, nucleus sampling

### Custom Parameters    max_tokens=500,        # Optional: max tokens to generate

    stop=["\\n\\n"],        # Optional: stop sequences

```python)

response = client.chat_completions_create(```

    model="llama3.2:3b",

    messages=[{"role": "user", "content": "Write a short story"}],#### `chat()`

    temperature=0.8,

    max_tokens=1000,Simplified chat interface for quick interactions.

    top_p=0.9,

    stop=["END", "###"]```python

)response = client.chat(

```    message="Explain photosynthesis",

    model="llama3.1:8b",           # Optional, default: "llama3.2:3b"

### Health Check    system_prompt="Be concise",    # Optional

    temperature=0.5                # Optional

```python)

health = client.health_check()```

print(f"Status: {health.status}")

print(f"Models: {len(health.ollama_models)}")#### `health_check()`

Check API status and available models.

Examples

Check the `examples/` directory for more usage examples:health = client.health_check()

- `basic_usage.py` - Simple chat completionsprint(health.status)

- `error_handling.py` - Comprehensive error handlingprint(health.ollama_models)

API Documentation

Data Models

Visit https://api.weycop.com/docs for complete API documentation.

Message

Support

- 📧 Email: [dev@weycop.com](mailto:dev@weycop.com)from weycop import Message

- 🐛 Issues: [GitHub Issues](https://github.com/weycop/weycop-python/issues)

- 📖 Docs: [https://docs.weycop.com](https://docs.weycop.com)msg = Message(role="user", content="Hello!")

# Roles: "system", "user", "assistant"

## License```



MIT License - see [LICENSE](LICENSE) file for details.#### ChatCompletion

Response object containing the completion result:

```python
completion = client.chat_completions_create(...)

print(completion.id)              # Unique request ID
print(completion.model)           # Model used
print(completion.usage.total_tokens)  # Token usage
print(completion.choices[0].message.content)  # Response text

Error Handling

import weycop
from weycop import AuthenticationError, RateLimitError, APIError

try:
    client = weycop.WeycopClient(api_key="invalid-key")
    response = client.chat("Hello")
except AuthenticationError:
    print("Invalid API key")
except RateLimitError:
    print("Rate limit exceeded")
except APIError as e:
    print(f"API error: {e}")
except weycop.WeycopError as e:
    print(f"Client error: {e}")

Examples

System Prompts

completion = client.chat_completions_create(
    model="llama3.1:8b",
    messages=[
        Message("system", "You are a SQL expert. Only respond with SQL code."),
        Message("user", "Get all users created in the last 30 days")
    ]
)

Multi-turn Conversation

messages = [
    Message("system", "You are a helpful math tutor."),
    Message("user", "What is 15 + 27?"),
]

# First response
completion = client.chat_completions_create(model="llama3.2:3b", messages=messages)
assistant_response = completion.choices[0].message.content
messages.append(Message("assistant", assistant_response))

# Follow-up question
messages.append(Message("user", "Now multiply that by 3"))
completion = client.chat_completions_create(model="llama3.2:3b", messages=messages)
print(completion.choices[0].message.content)

Context Management

# Use with statement for automatic cleanup
with weycop.WeycopClient(api_key="your-key") as client:
    response = client.chat("Hello!")
    print(response)
# Client is automatically closed

License

MIT License - see LICENSE file for details.

Support

Documentation: https://docs.weycop.com
GitHub Issues: https://github.com/weycop/weycop-python/issues
Email: dev@weycop.com

Project details

These details have not been verified by PyPI

Project links

Release history Release notifications | RSS feed

2.1.1

Oct 2, 2025

2.1.0

Oct 2, 2025

2.0.0

Oct 1, 2025

1.0.3

Sep 28, 2025

This version

1.0.2

Sep 28, 2025

1.0.0

Sep 28, 2025

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

weycop-1.0.2.tar.gz (15.5 kB view details)

Uploaded Sep 28, 2025 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

weycop-1.0.2-py3-none-any.whl (12.2 kB view details)

Uploaded Sep 28, 2025 Python 3

File details

Details for the file weycop-1.0.2.tar.gz.

File metadata

Download URL: weycop-1.0.2.tar.gz
Upload date: Sep 28, 2025
Size: 15.5 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for weycop-1.0.2.tar.gz
Algorithm	Hash digest
SHA256	`b801dca41703fcc4e3c4c782e688107098204ec05e1d88493c408aee953af3d5`
MD5	`51850decaf5fbb2f5787a4e97e8aefd8`
BLAKE2b-256	`74ab1bacc44d05823981cbd6e9f47e25305a57b693ef6db643b2ca1463d59f82`

See more details on using hashes here.

File details

Details for the file weycop-1.0.2-py3-none-any.whl.

File metadata

Download URL: weycop-1.0.2-py3-none-any.whl
Upload date: Sep 28, 2025
Size: 12.2 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for weycop-1.0.2-py3-none-any.whl
Algorithm	Hash digest
SHA256	`741b49d3a8f49a5e2ee68a60d66f4b3aeff4279dfd5cbb3b7ce19fd9e6563e0c`
MD5	`263832d2c42cf248d01f9033c1e559cc`
BLAKE2b-256	`5543cff937b1d8a77b6627e5f9563278ec4af0cf20f8f100a981e65dc0074600`

See more details on using hashes here.

weycop 1.0.2

Navigation

Verified details

Maintainers

Unverified details

Project links

Meta

Classifiers

Project description

WeyCP Python Client# WeyCP Python Client# WeyCP Python Client# WeyCP Python Client# WeyCP Python Client

Features

FeaturesOfficial Python client for WeyCP API - OpenAI-compatible chat completions using Ollama.

Installation

Quick Start

Synchronous Client

Supported Models

Error Handling)```bash

Advanced Usage

Custom Parameters

Health Check### Asynchronous Client```python

Supported Models

Error Handling)```bash

Advanced Usage

Custom Parameters

Health Check### Asynchronous Client```pythoncompletion = client.chat_completions_create(

Supported Models

Error Handling)print(f"Used {completion.usage.total_tokens} tokens")

Advanced usage### Asynchronous Usage

Health Check### Asynchronous Client

Examples

API Documentation

Data Models

Message

Support

Error Handling

Examples

System Prompts

Multi-turn Conversation

Context Management

License

Support

Project details

Verified details

Maintainers

Unverified details

Project links

Meta

Classifiers

Release history Release notifications | RSS feed

Download files

Source Distribution

Built Distribution

File details

File metadata

File hashes

File details

File metadata

File hashes

Features Official Python client for WeyCP API - OpenAI-compatible chat completions using Ollama.