Skip to main content
Version: Next

FAQs

Enterprise h2oGPTe is an AI-powered search assistant that helps you find answers to questions about your documents, websites, and workplace content - powered by H2O LLM.

  • With Enterprise h2oGPTe, finding what you need has never been easier
  • Ask a question, and Enterprise h2oGPTe will provide relevant results from across provided materials
  • Whether you're looking for a specific document or trying to understand a complex concept, Enterprise h2oGPTe can help you save time and effort

The following sections provide answers to frequently asked questions. If you have additional questions, please send them to cloud-feedback@h2o.ai.

General​

How does Enterprise h2oGPTe handle embedded images in PDFs?​

Enterprise h2oGPTe supports vision and language models out of the box and automatically determines which to use to answer a user's question. When using language models, optical character recognition (OCR) is used to extract text from any images. When using vision models, each page of a document is viewed as an image by the model.

Does Enterprise h2oGPTe have an API?​

Yes, Enterprise h2oGPTe has a Python API. To learn more, see Create an API key. A TypeScript API is available as well.

Which Embedding Models are supported in Enterprise h2oGPTe?​

When creating a new collection of data, users can choose from bge-large-en-v1.5, bge-m3, or instructor-large as the embedding model for their collection, with bge-large-en-v1.5 as the default. This decision is usually based on the language of their data and their users.

bge-large-zh-v1.5, multi-lingual-e5-large, or instructor-xl are also supported but need to be enabled by an admin.

We regularly update our platform with the latest embedding models to ensure optimal performance and state-of-the-art capabilities.

What is the Vector Database for Enterprise h2oGPTe (1) and can I customize it (2)?​

  1. The Vector Database for Enterprise h2oGPTe is called "Vex" and it is custom built by H2O.ai. Vex is a standalone vector "database" specifically designed for running similarity searches for Enterprise h2oGPTe. It serves as a storage and retrieval system for vector and text data.

    The current nearest neighbor algorithm used in Vex is hnswlib. Indexes are stored in hnswlib's native format and are created or loaded by the server on demand. This allows for efficient and fast similarity searches. The underlying text representation for each vector is stored in SQLite.

    Vex is architecturally similar to Chroma, which also utilizes hnswlib for thread-safety during index-writes. However, Vex includes several performance improvements compared to Chroma:

    1. It does not include unnecessary bindings to Clickhouse and DuckDB.
    2. It uses barebones Uvicorn (the core of FastAPI) instead of FastAPI, eliminating unnecessary overhead.
    3. It uses MsgPack instead of JSON for communication, reducing the bandwidth required for each request. This is particularly beneficial for compressing numpy arrays and UUIDs.
    4. It minimizes allocations in the query fast-path, avoiding unnecessary steps like Pydantic, and directly calling the library for binary deserialization.

  1. Customizability of Vex is limited, as it primarily focuses on delivering efficient similarity searches using its existing features. However, Enterprise h2oGPTe provides additional connectivity options to other Vector and full-text databases, allowing for more customization possibilities.

    Starting from Enterprise h2oGPTe 1.3.8, users can connect Enterprise h2oGPTe to hnswlib, Elastic Search, Milvus, Redis, and Qdrant for storing vector data, and SQLite, Redis and Elastic Search for storing text data. By default, HNSW and SQLite are used, other external databases are currently in experimental mode.

note

To learn how to customize the Vector Database, contact your admin.

Collections​

Can Enterprise h2oGPTe refer to several Collections to answer a query?​

Enterprise h2oGPTe is designed to access a specific Collection at a time, allowing users to ask detailed questions and receive precise answers based on the targeted data contained within that Collection. This focused approach ensures accuracy and relevance in the responses provided and ensures data security in the platform.

Documents​

What types of files can I use with Enterprise h2oGPTe beyond Documents?​

For a complete list of supported file types, see Supported file types for a Collection.

Are uploaded documents cleared after the user session, or do they persist?​

The uploaded documents are persisted until the user or admin explicitly deletes the document.

How are entitlements managed so that users are not querying each other's documents or the model is not picking chunks from other documents?​

Documents are private and accessible only to the user who uploaded them or via a publicly shared collection. An authenticated user client can only query resources they have access to.

Note: If you want to make documents public to all users accessing the system, change the collection from Private to Public (either in the UI or in the Python API). For more information, see Make a Collection public.

Chats​

Can I chat with a Collection in any language?​

Yes. For non-English chatting or documents, we recommend creating your collection with the Multilingual (bge-m3) embedding model which will be applied automatically to ingested data and user queries. You can also change the the Prompt Template to one of the 15+ supported languages for Retrival Augmented Generation or create your own template for new languages or use cases.

Feedback