Metadata-Version: 2.4
Name: llmfy
Version: 0.5.1
Summary: `LLMfy` is a framework for developing applications with large language models (LLMs).
Project-URL: Homepage, https://github.com/irufano/llmfy
Project-URL: Repository, https://github.com/irufano/llmfy
Author-email: irufano <irufano.official@gmail.com>
License-Expression: MIT
License-File: LICENSE
Keywords: ai,bedrock,google,llm,llm-abstraction,llm-framework,openai
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.11
Requires-Dist: pydantic
Provides-Extra: all
Requires-Dist: boto3; extra == 'all'
Requires-Dist: faiss-cpu; extra == 'all'
Requires-Dist: google-genai; extra == 'all'
Requires-Dist: numpy; extra == 'all'
Requires-Dist: openai; extra == 'all'
Requires-Dist: redis; extra == 'all'
Requires-Dist: sqlalchemy; extra == 'all'
Requires-Dist: typing-extensions; extra == 'all'
Provides-Extra: boto3
Requires-Dist: boto3; extra == 'boto3'
Provides-Extra: faiss-cpu
Requires-Dist: faiss-cpu; extra == 'faiss-cpu'
Provides-Extra: google-genai
Requires-Dist: google-genai; extra == 'google-genai'
Provides-Extra: numpy
Requires-Dist: numpy; extra == 'numpy'
Provides-Extra: openai
Requires-Dist: openai; extra == 'openai'
Provides-Extra: redis
Requires-Dist: redis; extra == 'redis'
Provides-Extra: sqlalchemy
Requires-Dist: sqlalchemy; extra == 'sqlalchemy'
Provides-Extra: typing-extensions
Requires-Dist: typing-extensions; extra == 'typing-extensions'
Description-Content-Type: text/markdown

![](LLMFY-LOGO.webp)

<div align="center">

  <a href="https://img.shields.io/github/actions/workflow/status/irufano/llmfy/release.yml">![llmfy](https://img.shields.io/github/actions/workflow/status/irufano/llmfy/release.yml?style=for-the-badge&logo=pypi&logoColor=blue&label=publish
  )</a>
  <a href="https://pypi.org/project/llmfy/0.5.1">![llmfy](https://img.shields.io/badge/llmfy-v0.5.1-31CA9C.svg?style=for-the-badge&logo=pypi&logoColor=yellow)</a>
  <a href="https://pypi.org/project/llmfy/">![llmfy](https://img.shields.io/pypi/v/llmfy?style=for-the-badge&label=latest&labelColor=691DC6&color=B77309)</a>
  <a href="">![python](https://img.shields.io/badge/python->=3.11-4392FF.svg?style=for-the-badge&logo=python&logoColor=4392FF)</a>

</div>

`LLMfy` is a flexible and developer-friendly framework designed to streamline the creation of applications powered by large language models (LLMs). It provides essential tools and abstractions that simplify the integration, orchestration, and management of LLMs across various use cases, enabling developers to focus on building intelligent, context-aware solutions without getting bogged down in low-level model handling. With support for modular components, prompt engineering, and extensibility, LLMfy accelerates the development of AI-driven applications from prototyping to production.

See complete documentation at [https://llmfy.readthedocs.io/](https://llmfy.readthedocs.io/)

## How to install

- Optional Library:
  - Install [openai](https://pypi.org/project/openai) to use OpenAI models — 🔸 optional.
  - Install [boto3](https://pypi.org/project/boto3/) to use AWS Bedrock models — 🔸 optional.
  - Install [numpy](https://pypi.org/project/numpy/) to use Embedding, `FAISSVectorStore` — 🔸 optional.
  - Install [faiss-cpu](https://pypi.org/project/faiss-cpu/) to use `FAISSVectorStore` — 🔸 optional.
  - Install [typing_extensions](https://pypi.org/project/typing-extensions/) to use state in `FlowEngine` — 🔸 optional.
  - Install [redis](https://pypi.org/project/redis/) to use `RedisCheckpointer` — 🔸 optional.
  - Install [SQLAlchemy](https://pypi.org/project/SQLAlchemy/) to use `SQLCheckpointer` — 🔸 optional. `SQLCheckpointer` supports both sync and async drivers for multiple databases:
      - PostgreSQL (async: [asyncpg](https://pypi.org/project/asyncpg/), sync: [psycopg2](https://pypi.org/project/psycopg2/)) — 🔸 optional.
      - MySQL (async: [aiomysql](https://pypi.org/project/aiomysql/), sync: [pymysql](https://pypi.org/project/PyMySQL/)) — 🔸 optional.
      - SQLite (async: [aiosqlite](https://pypi.org/project/aiosqlite/), sync: built-in) — 🔸 optional.

### Using UV
```sh
uv add llmfy
```

### Using pip
```sh
pip install llmfy
```

### Using github 

#### From a specific branch
```sh
# main
uv add git+https://github.com/irufano/llmfy.git@main
# or
pip install git+https://github.com/irufano/llmfy.git@main

# dev
uv add git+https://github.com/irufano/llmfy.git@dev
# or
pip install git+https://github.com/irufano/llmfy.git@dev
```

#### From a tag
```sh
# example tag version 0.4.3
uv add git+https://github.com/irufano/llmfy.git@v0.4.3
# or
pip install git+https://github.com/irufano/llmfy.git@v0.4.3
```

#### Github in requirements.txt

```txt
git+https://github.com/irufano/llmfy.git@dev
```

## How to use
### OpenAI models
To use `OpenAIModel`, requires install `"llmfy[openai]"` and add below config to your env:
- `OPENAI_API_KEY`

### AWS Bedrock models
To use `BedrockModel`, requires install `"llmfy[boto3]"` and add below config to your env:
- `AWS_ACCESS_KEY_ID` 
- `AWS_SECRET_ACCESS_KEY` 
- `AWS_BEDROCK_REGION`

### Google AI models
To use `GoogleAIModel`, requires install `"llmfy[google-genai]"` and add below config to your env:
- `GOOGLE_API_KEY`

## Example
### LLMfy Example
```python
from llmfy import (
    OpenAIModel,
    OpenAIConfig,
    LLMfy,
    Message,
    Role,
    LLMfyException,
)

def sample_prompt():
    info = """Irufano adalah seorang software engineer.
    Dia berasal dari Indonesia.
    Kamu bisa mengunjungi websitenya di https:://irufano.github.io"""

    # Configuration
    config = OpenAIConfig(temperature=0.7)
    llm = OpenAIModel(model="gpt-4o-mini", config=config)

    SYSTEM_PROMPT = """Answer any user questions based solely on the data below:
    <data>
    {info}
    </data>
    
    DO NOT response outside context."""

    # Initialize framework
    framework = LLMfy(llm, system_message=SYSTEM_PROMPT, input_variables=["info"])

    try:
        messages = [Message(role=Role.USER, content="apa ibukota china")]
       
        response = framework.invoke(messages, info=info)
        print(f"\n>> {response.result.content}\n")

    except LLMfyException as e:
        print(f"{e}")


if __name__ == "__main__":
    sample_prompt()
```

## Develop as Contributor

### Build package
```sh
uv build
```

### Trigger build and deploy to PyPI
```sh
# TAG_NAME must start with "v" (e.g., v1.0.0)
git tag -a [TAG_NAME] -m "[TAG_MESSAGE]"

# push tag to remote
git push origin [TAG_NAME]
```

### After deploy on local 
After the CI moves the tag, your local tag still points to the old commit. To sync:

```sh
git fetch --tags --force
```

The --force flag is needed because git fetch --tags alone won't update tags that already exist locally.

### Package Development on local
```sh
uv sync --group dev --group docs
```

or

```sh
uv sync --all-groups
```

### Mkdocs run on local

```sh
uv sync --group docs
```

```sh
# Serve on local
mkdocs serve

# Build docs
mkdocs build
```