Ragbits

Building blocks for rapid development of GenAI applications

Documentation | Contact

---

Features

🔨 Build Reliable & Scalable GenAI Apps

• Swap LLMs anytime – Switch between 100+ LLMs via LiteLLM or run local models.
• Type-safe LLM calls – Use Python generics to enforce strict type safety in model interactions.
• Bring your own vector store – Connect to Qdrant, PgVector, and more with built-in support.
• Developer tools included – Manage vector stores, query pipelines, and test prompts from your terminal.
• Modular installation – Install only what you need, reducing dependencies and improving performance.

📚 Fast & Flexible RAG Processing

• Ingest 20+ formats – Process PDFs, HTML, spreadsheets, presentations, and more. Process data using unstructured or create a custom provider.
• Handle complex data – Extract tables, images, and structured content with built-in VLMs support.
• Connect to any data source – Use prebuilt connectors for S3, GCS, Azure, or implement your own.
• Scale ingestion – Process large datasets quickly with Ray-based parallel processing.

🚀 Deploy & Monitor with Confidence

• Real-time observability – Track performance with OpenTelemetry and CLI insights.
• Built-in testing – Validate prompts with promptfoo before deployment.
• Auto-optimization – Continuously evaluate and refine model performance.
• Visual testing UI (Coming Soon) – Test and optimize applications with a visual interface.

What's Included?

• Core - Fundamental tools for working with prompts and LLMs.
• Document Search - Handles vector search to retrieve relevant documents.
• CLI - The ragbits shell command, enabling tools such as GUI prompt management.
• Guardrails - Ensures response safety and relevance.
• Evaluation - Unified evaluation framework for Ragbits components.
• Flow Controls - Manages multi-stage chat flows for performing advanced actions (coming soon).
• Structured Querying - Queries structured data sources in a predictable manner (coming soon).
• Caching - Adds a caching layer to reduce costs and response times (coming soon).

Installation

To use the complete Ragbits stack, install the ragbits package:

pip install ragbits

Alternatively, you can use individual components of the stack by installing their respective packages: ragbits-core, ragbits-document-search, ragbits-cli.

Quickstart

First, create a prompt and a model for the data used in the prompt:

from pydantic import BaseModel
from ragbits.core.prompt import Prompt

class Dog(BaseModel):
    breed: str
    age: int
    temperament: str

class DogNamePrompt(Prompt[Dog, str]):
    system_prompt = """
    You are a dog name generator. You come up with funny names for dogs given the dog details.
    """

    user_prompt = """
    The dog is a {breed} breed, {age} years old, and has a {temperament} temperament.
    """

Next, create an instance of the LLM and the prompt:

from ragbits.core.llms.litellm import LiteLLM

llm = LiteLLM("gpt-4o")
example_dog = Dog(breed="Golden Retriever", age=3, temperament="friendly")
prompt = DogNamePrompt(example_dog)

Finally, generate a response from the LLM using the prompt:

response = await llm.generate(prompt)
print(f"Generated dog name: {response}")

How Ragbits documentation is organized

• Quickstart - Get started with Ragbits in a few minutes
• How-to guides - Learn how to use Ragbits in your projects
• CLI - Learn how to run Ragbits in your terminal
• API reference - Explore the underlying API of Ragbits

License

Ragbits is licensed under the MIT License.

Contributing

We welcome contributions! Please read CONTRIBUTING.md for more information.