Getting started with Verba, the open-source RAG framework, is a breeze. You have multiple options to install and set it up, depending on your preference and requirements.

Install via pip

The easiest way to get started is by installing Verba using pip. Simply run the following command in your terminal or command prompt:

pip install golden-verba

Once the installation is complete, you can launch Verba by typing verba start in your terminal. This will start the Verba application, and you can access it by navigating to http://localhost:8000 in your web browser.

Use Docker

Verba also provides a Docker image, making it easy to deploy and run the application in a containerized environment. To use the Docker image, follow these steps:

1. Install Docker on your system if you haven't already.
2. Pull the Verba Docker image:

   docker pull goldenverba/verba
   

3. Run the Verba container:

   docker run -p 8000:8000 goldenverba/verba
   

4. Access the Verba application at http://localhost:8000.

Build from Source

If you prefer to build Verba from the source code, you can follow the instructions provided in the Verba GitHub repository. This option allows you to customize the application and contribute to its development.

Configure API Keys

Verba supports various language models, including OpenAI, Cohere, and Anthropic. To use these models, you'll need to provide the corresponding API keys. You can set the API keys in the Verba admin console, which you can access by navigating to http://localhost:8000/admin.

With these installation and setup options, you can quickly get started with Verba and start exploring the power of the RAG framework for your data processing and question-answering needs.

Verba is an open-source framework that offers a comprehensive and user-friendly interface for working with large language models (LLMs) and Retrieval Augmented Generation (RAG) techniques. Here's a closer look at some of its key features:

Document Management:

• Verba allows you to easily import and manage your data, including PDFs, Markdown files, and more.
• The chunking system ensures that your content is broken down into manageable segments, optimizing the performance of your LLM.
• Verba supports a variety of embedding models, including Sentence Transformer and Cohere, allowing you to work with multilingual content.

Semantic Search:

• The Retriever Manager in Verba is responsible for ensuring that the most relevant content is retrieved for your queries.
• By leveraging the power of LLMs, Verba can understand the context and meaning of your questions, providing precise and detailed answers.
• The intuitive user interface makes it easy to explore your data and find the information you need.

Text Generation:

• Verba's Generative Module allows you to generate text based on the retrieved content, such as creating Facebook ads or poems.
• You can choose from various language models, including OpenAI and Cohere, to generate the desired output.
• This feature enables you to quickly and efficiently create content tailored to your specific needs.

Verba's modular and extensible design allows you to customize and expand its capabilities to suit your unique requirements. Whether you're working with technical documentation, research papers, or any other type of content, Verba provides a powerful and user-friendly solution for extracting insights and generating relevant text.

Verba's modular design allows you to easily integrate different embedding and retrieval models to suit your specific needs. This flexibility is a key strength of the framework.

The embedding manager in Verba supports multiple models, including the powerful Sentence Transformer and Cohere multilingual models. This means you can work with documents in various languages and still retrieve relevant information, even if your query is in a different language.

The retriever manager is responsible for ensuring that the most relevant context is retrieved for a given query. By modularizing this component, Verba allows you to experiment with different retrieval strategies and find the one that works best for your use case.

Whether you're working with technical documentation, research papers, or any other type of unstructured data, Verba's modular architecture empowers you to build a customized RAG pipeline that delivers precise and detailed answers to your queries.

Verba is an open-source framework that revolutionizes the way we utilize Retrieval Augmented Generation (RAG) with our documents or files. This powerful tool offers an end-to-end, streamlined, and user-friendly interface to explore your data set and extract insights with ease.

With Verba, you can easily integrate it into your local environment or deploy it using Docker. The framework provides a modular ecosystem, allowing you to leverage various language models, such as OpenAI, Cohere, and Sentence Transformer, to transform your data into embeddings and retrieve the most relevant context for your queries.

The key features of Verba include:

1. Data Ingestion and Chunking: Verba's reader manager and chunker manager ensure that your data is properly imported and chunked, optimizing the context retrieval process.

2. Flexible Embedding Options: Verba supports multiple embedding models, including Sentence Transformer and Cohere's multilingual model, allowing you to work with diverse data sources.

3. Contextual Retrieval: The retriever manager in Verba guarantees that your queries are matched with the most relevant documents, providing precise and detailed answers.

4. Generative Capabilities: Verba's generative module enables you to generate text based on the retrieved information, such as creating Facebook ads or poems from your documents.

5. Modular and Extensible: Verba is designed to be open-source and modular, allowing you to extend its functionality and integrate it with your existing workflows.

Whether you're working with technical documentation, blog posts, or any other type of data, Verba empowers you to streamline your business processes and improve efficiency. By leveraging the power of RAG and large language models, Verba helps you extract valuable insights and generate tailored content with ease.

Explore the full potential of Verba and revolutionize the way you interact with your data. Get started today and experience the benefits of this innovative open-source framework.

Verba is an impressive open-source framework that revolutionizes the way we utilize Retrieval Augmented Generation (RAG) with our documents or files. This tool offers an end-to-end streamlined and user-friendly interface, allowing users to easily explore their data sets and extract valuable insights.

The modular architecture of Verba enables users to extend its capabilities further, making it a highly customizable and versatile solution. With support for various language models, including OpenAI and Cohere, Verba provides flexibility in handling documents in different languages.

The key features of Verba include:

1. Data Ingestion: Verba seamlessly handles the import of various file formats, including PDFs and Markdown documents, and efficiently chunks the data for optimal processing.

2. Embedding and Retrieval: Verba leverages advanced embedding models, such as Sentence Transformer and Cohere Multilingual, to transform the data into embeddings, enabling precise retrieval of relevant information based on user queries.

3. Text Generation: The generative module of Verba allows users to generate text from the retrieved information, enabling tasks like creating Facebook ads or poems based on the provided content.

4. Modular Design: Verba's modular architecture allows users to easily integrate their preferred language models and customize the framework to suit their specific needs.

Overall, Verba is a powerful and user-friendly open-source tool that simplifies the process of working with RAG, making it accessible to a wide range of users, from researchers to content creators. Its flexibility and extensibility make it a valuable asset in the world of natural language processing and data exploration.