GPT-Assistant Library
The GPT-Assistant Library is a Python-based toolkit for building intelligent personal assistants powered by OpenAI's GPT models. This library simplifies the integration of conversational AI into your applications, making it easier than ever to create chatbots, virtual assistants, and more.
Key Features
- Seamless integration with GPT-3 and GPT-4 models.
- Easily manage conversations and user interactions.
- Support multiuser chat history support
- Customizable and extensible to suit your specific needs.
- Developer-friendly API for smooth integration into your projects.
Installation
pip install gpt-assistant-lib
Configuration
To set up the assistant, you need an API key and to create a system prompt.
Obtain API key
Go to Openai website
System prompt
It will define your assistant behaviour. More info you can find in documentation
History
The library maintains a conversation history that the assistant relies on to understand and maintain context during interactions. This conversation history is included in every request sent to OpenAI. A larger history size allows the assistant to remember more context, enhancing its ability to engage in meaningful conversations. However, it's important to note that larger conversation histories can result in increased API call costs.
Usage
import gpt_assistant_lib
openai_api_key = "your_openai_api_key"
initial_prompt = "You are a helpful assistant."
max_history_size = 5
history_lifetime = 600 # 10 minutes
assistant = gpt_assistant_lib.build_assistant(openai_api_key, initial_prompt, max_history_size, history_lifetime)
while True:
user_input = input("You: ")
assistant_response = assistant.exchange("any", user_input)
print(f"Assistant: {assistant_response}")
Development
Run with enabled virtual environment
Autoformat source code
task format
Run all linters
task lint
Run unit tests
task test
Run all linters and unit tests
task all
License
This project is licensed under the MIT License
Metadata
Release files for gpt-assistant-lib 0.3.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| gpt_assistant_lib-0.3.1.tar.gz | 5.4 kB | Without provenance | Details for gpt_assistant_lib-0.3.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| gpt_assistant_lib-0.3.1-py3-none-any.whl | Python 3 | none | any | Details for gpt_assistant_lib-0.3.1-py3-none-any.whl |
Total release size: 12.7 kB
Release files / gpt_assistant_lib-0.3.1.tar.gz
| Download URL | gpt_assistant_lib-0.3.1.tar.gz |
|---|---|
| Size | 5.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9760db7943d6178c845907de677c8a86b46fe6e2e4ac6f70dbeb046c626b743f
|
|
BLAKE2b-256 checksum How to use checksums |
e2bb67bb7d60446e2e3396fd4ac011aae54c9646788930dc30ee05c255746c78
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.5.1 CPython/3.11.3 Darwin/22.6.0
|
Release files / gpt_assistant_lib-0.3.1-py3-none-any.whl
| Download URL | gpt_assistant_lib-0.3.1-py3-none-any.whl |
|---|---|
| Size | 7.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
39058ce0d8246d55a93fdf0f7d999c7823ee04d7c3b14fc227a7613cb0be1a50
|
|
BLAKE2b-256 checksum How to use checksums |
1b47b6e984af5e5dfde183c31288538fd3e555af278116cf3c822b6039128190
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.5.1 CPython/3.11.3 Darwin/22.6.0
|
Security for gpt-assistant-lib 0.3.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.