Kamiwaza Stack Community Edition
 

Our community Edition is limited to a single node (non-clustered) so enjoy a near full feature Gen-AI stack to develop on your laptop or run on a server!

Community Edition Download here

We love feed back and provide support through our Discord Kamiwaza Community Server join by clicking invite code below:
‍
Discord invite code here



Feb 1 - 2024

Feb 1

Our Kamiwaza community edition 0.1.0 is available by clicking contact above and filling out the request form. Currently only available for Mac's with Metal processors and Linux with Nvidia RTX cards.

‍

‍

March - 2024

March 26

Our new release of the Kamiwaza community edition 0.2.0 is now in broad availability through a simple download!

Support provided through our Discord server - https://discord.gg/cVGBS5rD2U

This full feature release is only limited by a single node non-clustered now including:

  • Model repository with hf hub integration
  • Model deployment from repository, supporting llama.cpp and vLLM
  • Helper middleware (optional) for embeddings, vector databases, retrieval
  • Retrieval middleware that stitches together catalog+secret management+retrieval+pipelines on Ray
  • Pre-integrated components with an installer for both OSX / Linux
  • Support for CPU and GPU on both OSX and Linux, both arm64 and amd64/x86_64 platforms
  • Notebook environment pre-integrated with the Kamiwaza tools
  • REST API for building applications
  • Response React UI (using the REST API) for viewing and managing models, model deployments, catalog items, and more
  • Pre-integrated and installer auto-deploys Acryl Datahub (catalog), Milvus as a vectordb, and CockroachDB for managing Kamiwaza items
  • Built with Ray (Ray Serve, Ray Data on top of Ray) to allow large parallel pipelines

Kamiwaza is also announcing the open-source release of AgentZero, an internal ChatBot tool built by Kamiwaza as the first leg of a chatbot with RAG and Agent framework built in. This first release supports a fully functional responsive chatbot web interface as a FastAPI app, with:

https://github.com/kamiwaza-ai/agentzero

  1. Familiar sidebar history+conversations
  2. Support for OpenAI and openai-compatible model endpoints (including Kamiwaza model deployments)
  3. Code highlighting
  4. Token streaming
  5. Model selector (including the ability to change models mid-conversation)
  6. Automatic retrieval functions; if you have Kamiwaza community edition installed (not required for AgentZero), your model deployments will auto-populate, as well your data sources for RAG retrieval

‍

Coming Soon

Kamiwaza Stack Community Edition

Our community Edition is limited to a single node
(non-clustered) so enjoy a near full feature Gen-AI stack to develop
on your laptop or run on a server!

We love feed back and provide support through our Discord Kamiwaza
Community Server join by clicking invite code below:

Community Edition HereJoin Community (Discord)

New Release


‍

Our new release of the Kamiwaza community edition 0.3.0 is now in broad availability through a simple download!

https://github.com/kamiwaza-ai/kamiwaza-community-edition/


Support provided through our Discord server -
https://discord.gg/cVGBS5rD2U

‍Kamiwaza is also moving to an iterative release schedule with minor releases expected every 2-3 weeks to capture bugs and additional feature adds to our community edition for testing.

All our documentation on each release is updated and available at:https://github.com/kamiwaza-ai/kamiwaza-docs

August 1 - 2024

‍

Release Changes and Notes

  1. Architecture and Compatibility:
    • Added support for ARM64 architecture for broader hardware compatibility.
    • Upgraded various integrated components to more recent versions, enhancing overall performance and functionality.
    • Added support for Ampere-optimized inference, enhancing performance on Ampere systems.
  2. Improved Deployment and Configuration Management:
    • Introduced a faster and more scalable runtime configuration management component, improving deployment flexibility.
    • Enhanced Docker Compose files to support more dynamic and flexible network configurations.
  3. Advanced Error Handling and Logging:
    • Improved error handling across the frontend for a better user experience.
    • Enhanced logging throughout the system to facilitate better debugging and transparency.
  4. Scalability and Flexibility Enhancements:
    • Introduced load balancing with unified endpoints to enhance network scalability and deployment flexibility.
    • Added health check routines for improved monitoring and reliability.
    • Improved networking with interface, route, and DNS detection.
    • Unified entry points and enhanced support for SSL, ensuring secure and efficient connections.
    • Added single host/port multi-node scaled OpenAI-compatible model endpoints, improving scalability and ease of deployment.
  5. Optimized Performance and Efficiency:
    • Enhanced model configuration deployment processes with advanced options for streamlined user input.
    • Improved environmental setup and build processes for better developer efficiency.
    • Added services stop script to complement service startup; not that you’d ever want to turn Kamiwaza off.

Kamiwaza is also announcing the open-source release of AgentZero, an internal ChatBot tool built by Kamiwaza as the first leg of a chatbot with RAG and Agent framework built in. This first release supports a fully functional responsive chatbot web interface as a FastAPI app, with:

https://github.com/kamiwaza-ai/agentzero

  1. Familiar sidebar history+conversations
  2. Support for OpenAI and openai-compatible model endpoints (including Kamiwaza model deployments)
  3. Code highlighting
  4. Token streaming
  5. Model selector (including the ability to change models mid-conversation)
  6. Automatic retrieval functions; if you have Kamiwaza community edition installed (not required for AgentZero), your model deployments will auto-populate, as well your data sources for RAG retrieval

March 26 - 2024

Our new release of the Kamiwaza community edition 0.2.0 is now in broad availability through a simple download! 


Support provided through our Discord server - https://discord.gg/cVGBS5rD2U
‍This full feature release is only limited by a single node non-clustered now including:

  1. Model repository with hf hub integration
  2. Model deployment from repository, supporting llama.cpp and vLLM
  3. Helper middleware (optional) for embeddings, vector databases, retrieval
  4. Retrieval middleware that stitches together catalog+secret management+retrieval+pipelines on Ray
  5. Pre-integrated components with an installer for both OSX / Linux
  6. Support for CPU and GPU on both OSX and Linux, both arm64 and amd64/x86_64 platforms
  7. Notebook environment pre-integrated with the Kamiwaza tools
  8. REST API for building applications
  9. Response React UI (using the REST API) for viewing and managing models, model deployments, catalog items, and more
  10. Pre-integrated and installer auto-deploys Acryl Datahub (catalog), Milvus as a vectordb, and CockroachDB for managing Kamiwaza items
  11. Built with Ray (Ray Serve, Ray Data on top of Ray) to allow large parallel pipelines

Community Edition

Our Kamiwaza community edition 0.1.0 is available by clicking contact above and filling out the request form. Currently only available for Mac's with Metal processors and Linux with Nvidia RTX cards.

Feb 1 - 2024

Have Additional Questions
Contact us!

Click below to contact us or email us at support@kamiwaza.ai

Get in touch

Download Our Kamiwaza Community Edition Works on your Laptop  Desktop or Server

Get model management, a prompt library, retrieval tools for RAG, along with typical things like a notebook server and local inference with preconfigured tools - and the knowledge that you can go to production without having to re-platform what you’ve built.

Join our Kamiwaza Community on Discord for support on the Community Edition or to explore use cases and talk shop with others on how Enterprises are making the Journey to 1 Trillion Inferences a day!
‍

Community Edition Here Join Community (Discord)