v0.12.10

Version 0.12.10

This release includes critical bug fixes to enhance the functionality and stability of the document store features.

New Features

• No new features were added in this version.

Bug Fixes

• Fixed an issue in LanceDBDocStore where setting use_tantivy to False prevents a ValueError during FTS index creation by ensuring field_names is a string. (89a6869) (Eric Ma)
• Corrected a ValueError in create_fts_index by changing the field_names argument from a list to a string when use_tantivy is set to False. (4ad2dab) (Eric Ma)

Deprecations

• No deprecations in this version.

v0.12.9

Version 0.12.9

This release includes a refactor to enhance flexibility in configuration, along with dependency updates to improve stability and security.

New Features

• Refactored summarize_web_results in llamabot/components/tools.py to utilize an environment variable for setting the default model name, enhancing configurability and reducing hard-coded values. (aa3ad4) (Eric Ma)

Bug Fixes

• None

Deprecations

• None

Dependency Updates

• Updated prefix-dev/setup-pixi from version 0.8.8 to 0.8.10 to incorporate the latest patches and improvements. This update includes minor enhancements and bug fixes as detailed in the dependency's release notes. (0d566f) (dependabot[bot])

v0.12.8

Version 0.12.8

This release introduces new dependencies and enhancements in the document store functionalities, improving performance and relevance of search results.

New Features

• Added the rerankers package version 0.10.0 as a new dependency to enhance functionality across multiple environments and platforms. This update also necessitated updates to other dependencies. (5323b31) (Eric Ma)
• Replaced RRFReranker with ColbertReranker in LanceDBDocStore for improved document retrieval and added a new example notebook to demonstrate its usage. This change enhances the document retrieval capabilities by utilizing a more efficient reranker. (2f4a607) (Eric Ma)

Refactorings

• Refactored the document store component by replacing FTS index creation with table optimization for better performance and added reranking to the retrieve method to improve search result relevance. (77d1536) (Eric Ma)

Dependencies

• Updated llamabot package hash due to changes in dependencies, ensuring compatibility and stability with the new rerankers package. (5323b31) (Eric Ma)

v0.12.7

Version 0.12.7

This release introduces new features enhancing documentation and example interfaces, improves the configurability of embedding models in LanceDBDocStore, and includes several bug fixes and refinements in documentation and codebase.

New Features

• Added a new example script demonstrating how to build an interactive chat interface using LlamaBot and Marimo, complete with a grid layout JSON file for the UI. (133f12e) (Eric Ma)
• Introduced configurable embedding model settings in LanceDBDocStore, allowing users to specify embedding registries and models, enhancing customization. (3356016) (Eric Ma)

Bug Fixes

• Fixed the initialization of the Vector field in LanceDBDocStore to use the correct dimensions, ensuring proper setup. (3595285) (Eric Ma)
• Updated the embedding function in LanceDBDocStore to use 'minishlab/potion-base-8M' for improved performance and compatibility. (56532ac) (Eric Ma)

Documentation Updates

• Removed outdated note about GPT4 authorship from the QueryBot tutorial, ensuring clarity and accuracy in documentation. (a00798a) (Eric Ma)
• Updated the QueryBot tutorial to recommend explicit document store and chat memory management, replacing GPT-4 specific instructions with more general LLM usage and introducing LanceDBDocStore for better management. (046286c) (Eric Ma)
• Added comprehensive documentation for the new LlamaBot documentation chat interface example, including setup and usage instructions. (133f12e) (Eric Ma)
• Enhanced the QueryBot tutorial to demonstrate how to configure embedding model settings in LanceDBDocStore, complete with default settings and customization options. (3356016) (Eric Ma)

Refinements

• Simplified the embedding function initialization in LanceDBDocStore by removing redundant imports and optimizing the creation process. (2db2f46) (Eric Ma)
• Commented out unused hypothesis strategies import and related unused code in test_docstore.py, cleaning up the test suite. (bef8924) (Eric Ma)

v0.12.6

Version 0.12.6

This release includes several enhancements and new features aimed at improving the functionality and user experience of our software. Key updates include refinements in agent setup, benchmarking tools, and significant improvements in our logging and UI components.

New Features

• Introduced a new HTML endpoint for rendering the main experiment view page, enhancing user interaction with experiment data. (47c4be4) (Eric Ma)
• Added a main prompt comparison page endpoint to facilitate easier access and comparison of different prompts. (be39a28) (Eric Ma)
• Implemented detailed run metadata tracking for AgentBot, enhancing monitoring and debugging capabilities. (98c9694) (Eric Ma)
• Added run metadata tracking for StructuredBot to monitor validation attempts and outcomes, improving reliability and performance insights. (5f57e63) (Eric Ma)
• Enhanced QueryBot with run metadata tracking to provide detailed insights into query performance and efficiency. (3849731) (Eric Ma)
• Introduced run metadata tracking for SimpleBot, allowing detailed monitoring of call metrics and tool usage. (d6418dc) (Eric Ma)
• Added new tools and metrics for agent performance measurement in agents.py, improving the setup and benchmarking process. (2a49bde) (Eric Ma)
• Updated agentbot tutorial to include the use of the gpt-4.1 model and introduced a section on using the planner bot. (d1f48ab) (Eric Ma)
• Added column visibility controls for metrics in the experiment details view, enhancing user interface flexibility. (0b49f33) (Eric Ma)

Bug Fixes

• No specific bug fixes were noted in this release.

Deprecations

• No deprecations were introduced in this release.

v0.12.5

Version 0.12.5

This release includes significant enhancements in UI component reusability, improvements in tool handling and logging within the AgentBot system, and general codebase optimizations for better maintainability and performance.

New Features

• Enhanced UI component guidelines with detailed instructions on using Jinja2 macros for consistency and reusability. This update facilitates the use of shared UI components across different templates, ensuring a consistent and maintainable codebase. (8eadbe) (Eric Ma)
• Introduced a new 'message_expansion' macro to encapsulate message display logic, replacing inline HTML and promoting code reuse across templates. (0dc239) (Eric Ma)
• Refactored AgentBot tool handling and iteration logic to simplify initialization and enhance the logging and message serialization processes. A new tool call display feature was also added to the web UI for better visibility of operations. (c704cd) (Eric Ma)
• Added a new 'respond_to_user' tool in AgentBot to streamline responses to users, ensuring immediate and accurate replies. This feature also includes updates to tool handling and logging to improve the overall functionality and reliability of the system. (24ec8a) (Eric Ma)

Bug Fixes

• None listed in this release.

Deprecations

• None listed in this release.

v0.12.4

Version 0.12.4

This release includes significant enhancements to the LlamaBot framework, improving tool handling, debugging, and agent setup. Additionally, the testing framework has been updated to support new schema structures.

New Features

• Refactored the LlamaBot agents notebook to update dependencies and improve agent setup, enhancing example usage with new capabilities like dataset analysis and sports predictions. (ec344d6) (Eric Ma)
• Updated the AgentBot to support an optional planning bot and improved tool call handling with enhanced logging and concurrency management. (d28cce4) (Eric Ma)
• Modified the tool decorator to support a nested function schema structure, improving JSON schema consistency across tools. (d33d28) (Eric Ma)

Bug Fixes

• None

Deprecations

• None

This version continues to refine the functionality and usability of the LlamaBot, ensuring better performance and easier integration in various applications.

v0.12.3

Version 0.12.3

This release introduces significant enhancements to the AgentBot and LlamaBot components, improving their capabilities in autonomous planning, execution, and precise summarization. Additionally, a new notebook demonstration for AgentBot usage is included, showcasing practical applications with various tools and models.

New Features

• Added a notebook demonstrating how to use AgentBot with specific tools and models, including examples for summarizing album ratings, training classifiers, and making sports predictions. (2fcb347) (Eric Ma)
• Introduced a new system prompt for a summarization bot that provides focused and professional summaries of web content, along with customizable bot configuration options. (7c3dc11) (Eric Ma)
• Enhanced AgentBot with autonomous planning and execution capabilities, including default system prompts and a planner bot for strategic task management. (d95e20f) (Eric Ma)

Bug Fixes

None in this release.

Deprecations

None in this release.

v0.12.2

Version 0.12.2

This minor release includes a simplification of the .gitignore file creation process within the ensure_db_in_gitignore function, enhancing maintainability and clarity.

New Features

• Simplified the creation of the .gitignore file in the .llamabot directory to only ignore all files within it, removing unnecessary comments and exceptions. (f7bfe9) (Eric Ma)

Bug Fixes

Deprecations

Please note that this release does not include any new bug fixes or deprecations.

v0.12.1

Version 0.12.1

This release includes several enhancements and bug fixes that improve the functionality and documentation of the project, along with dependency updates.

New Features

• Introduced new agent capabilities and a notebook demonstration for LlamaBot, showcasing advanced functionalities like dataset downloading, model training, and cross-validation. (9aeddb5) (Eric Ma)
• Added a new example notebook to demonstrate LlamaBot functionalities, enhancing the interactive experience and usability of the bot. (f4cba9) (Eric Ma)

Bug Fixes

• Updated the model name and improved documentation in the introductory notebook to enhance clarity and user understanding. (e4c1db) (Eric Ma)
• Removed unnecessary timeout checks in test_write_and_execute_script_schema, simplifying the test process and removing irrelevant assertions. (22ec7e) (Eric Ma)
• Updated the model name and improved documentation in the introductory notebook, ensuring accurate and clear information is presented. (7a6e70) (Eric Ma)

Enhancements

• Updated dependencies and model names to keep the project up-to-date with the latest versions and standards, ensuring better performance and compatibility. (1ec551) (Eric Ma)
• Updated the llamabot package to its latest version, ensuring the project benefits from the latest improvements and bug fixes. (366f41) (Eric Ma)
• Added the 'ty' package to dependencies to ensure all necessary libraries are available for the project's functionality. (a5d3d3) (Eric Ma)
• Improved code formatting and readability in notebooks, making the code cleaner and easier to understand. (ac65e6) (Eric Ma)
• Moved import statements to cell definitions in notebooks to avoid potential naming conflicts and improve modularity. (425466) (Eric Ma)

Dependency Updates

• Updated the llamabot package to ensure compatibility with the latest features and improvements. (366f41) (Eric Ma)
• Added the 'ty' package to the project's dependencies to support new functionalities. (a5d3d3) (Eric Ma)

Documentation

• Improved documentation in the introductory notebook to enhance user understanding and provide clearer instructions. (7a6e70) (Eric Ma)
• Updated and improved documentation across various notebooks, ensuring all information is current and clear. (e4c1db) (Eric Ma)