Releases: phidatahq/phidata
v2.7.7
Changelog
New Features:
- Image-to-Image Generation Support: Extended FalTools to support image-to-image generation.
- MongoDB Integrations: Added MongoDB support across agent storage, agent knowledgebase, agent memory, and workflow storage.
- Download Image Utility: Introduced a utility to download agent-generated images directly for enhanced workflows.
Improvements:
- Audio Transcript Handling: Refined the handling of audio transcripts to ensure accurate message output when processing audio files
- Optimized Chunking: Enhanced fixed and recursive chunking methods to improve document processing performance.
- HuggingFace Embedder: Resolved compatibility issues with HuggingFace embedder for better reliability.
- Ollama Embedder: Upgraded the Ollama embedder for more robust and efficient embedding capabilities.
- OpenAI o1 Model Specification Support: Added support for OpenAI o1 model specifications, enabling compatibility with the latest OpenAI features.
- Spider Tool Improvements: Addressed performance issues with the Spider tool to enhance reliability.
- LanceDB Enhancements: Added support for accessing existing database tables in LanceDB
- Github tool repo creation: Added support for repo creation via the Github tool.
- ScrapeGraph tool addition: Adds integration with ScrapeGraph AI for smart web scraping and markdown conversion capabilities.
Bug Fixes:
- OpenAI rejecting functions with too large description: This issue was discovered with Composio tools, but affected all tools. Resolved and made tool definitions better match JSON Schema.
- Google Embedder Compatibility: Fixed an issue with Pydantic 2.10.x that caused the rejection of the Google embedder, restoring full functionality.
- ChromaDB Upsert Issue: Resolved bugs that caused errors during upsert operations in ChromaDB.
- Async Error Messaging: Improved error messages for unsupported async operations in models.
- Gemini Tool Parameters: Fixed an issue with parameter handling in Gemini tools
What's Changed
- Desi Vocal audio tool by @anuragts in #1608
- refactor: passing down ssl verification as it's available in DDGS class by @FaresKi in #1604
- Image to image agent by @anuragts in #1628
- Self evaluation workflow example by @manthanguptaa in #1638
- lance-db-deepcopy-phi-2239 by @ysolanky in #1690
- Gemini list as tool call param fix phi 2238 by @ysolanky in #1687
- Example / Game Generator (PHI-2194) by @dirkbrnd in #1579
- Fix gemini client type by @dirkbrnd in #1680
- "Fix upsert_available to return True for ChromaDB" by @yuvii007 in #1699
- fixed HuggingFace Embedder #1654 by @DarkDk123 in #1670
- Refactor ollama get_embedding_and_usage to use get_embedding method by @DarkDk123 in #1677
- chore(spidertools): Added support for optional API parameters and setting default crawl limit by @gbertb in #1649
- Readme/Dev Docs Generator by @anuragts in #1708
- Update recursive.py by @Gruhit13 in #1706
- Update fixed.py by @Gruhit13 in #1705
- Update fixed.py by @Gruhit13 in #1704
- lancedb-fix-phi-2240 by @ysolanky in #1691
- video captioning tool by @Ayush0054 in #1593
- Content Creator Agent Workflow by @Itz-Antaripa in #1614
- Add download images util by @dirkbrnd in #1712
- media trend analysis agent by @Ayush0054 in #1679
- Feat/openai transcript by @ysolanky in #1632
- Recruitment Workflow Example by @manthanguptaa in #1639
- Fix: handle error when model doesn't support async by @manthanguptaa in #1641
- AI Research Agent by @Itz-Antaripa in #1656
- Add MongoDB support [VectorDB] [v0: basic RAG] by @ranfysvalle02 in #1505
- Support o1 developer message format by @dirkbrnd in #1717
- Feat: Add upload support for files on playground by @manthanguptaa in #1564
- Add support for mongodb for Agent, Memory and Workflow Storage by @manthanguptaa in #1660
- convert a video to shorts by @pritipsingh in #1658
- created qa_agents_workflow by @Itz-Antaripa in #1637
- Coding agent workflow by @Itz-Antaripa in #1686
- Fix issue with duplicate contents in one document list by @Tesla2000 in #1256
- fix knowledge by @ysolanky in #1728
- 🕷️ feat: scrapegraph tools integration by @PeriniM in #1657
- Added Method for Repo Creation by @srexrg in #1655
- Clean up docstring and add descriptions to parameters by @dirkbrnd in #1723
New Contributors
- @FaresKi made their first contribution in #1604
- @yuvii007 made their first contribution in #1699
- @DarkDk123 made their first contribution in #1670
- @gbertb made their first contribution in #1649
- @Gruhit13 made their first contribution in #1706
- @Itz-Antaripa made their first contribution in #1614
- @ranfysvalle02 made their first contribution in #1505
- @PeriniM made their first contribution in #1657
Full Changelog: v2.7.6...v2.7.7
Contributors
Assets 2
v2.7.6
Changelog
Extending Vector database support
This update adds new vector database integrations, improvements to DuckDuckGo tool and Gemini model and new cookbooks.
New Features
Cassandra Vector Database: Introduced support for Apache Cassandra as a Vector Database, leveraging CassIO for vector storage and retrieval.
ClickHouse as a Vector Database: Added support for ClickHouse as a Vector Database
Improvements
DuckDuckGo Modifier: Added a modifier parameter to the DuckDuckGo tool, allowing users to refine searches with site-specific queries, file type filters, and safe search toggles.
Enhanced Error Handling for python-docx: Improved error messaging for scenarios where the python-docx library is not installed, providing clearer guidance and smoother debugging.
Bug Fixes
Qdrant Default Embedder : Removed OpenAI as the default embedder for Qdrant, enabling user-configurable embeddings.
Gemini Import Fix : Fixed an issue where missing OpenAI library dependencies caused errors when using Gemini.
What's Changed
- OpenAI audio agent by @ysolanky in #1631
- Fix typos in debug output by @chug2k in #1661
- fix qdrant default embedder by @ysolanky in #1643
- gather agents example by @ysolanky in #1633
- Add Cassandra Integration as Vector Database for Phidata by @VedantS20 in #1447
- #1326: Add clickhouse as a VectorDb. by @vodkar in #1503
- dream decoder agent by @Ayush0054 in #1561
- chore: update assistant.py by @eltociear in #1648
- Improvement: Better error handling when python-docx isn't installed by @manthanguptaa in #1640
- Added a Legal Advisor Agent by @srexrg in #1629
- Very minor change - Just ignoring all possible virtual envs as people… by @gauravdhiman in #1620
- Add optional ddg modifier by @sroecker in #1580
- Gemini import fix by @ysolanky in #1663
New Contributors
- @chug2k made their first contribution in #1661
- @VedantS20 made their first contribution in #1447
- @srexrg made their first contribution in #1629
- @sroecker made their first contribution in #1580
Full Changelog: v2.7.5...v2.7.6
Contributors
Assets 2
v2.7.5
This update introduces the Confluence tool for collaboration, improves tool compatibility, and resolves deep copy issues for Ollama chat agents.
New Features:
- Confluence Tool: Added a new tool using the Atlassian Confluence SDK, enabling operations such as listing pages in a space, creating and updating pages, retrieving page content by title, and getting space details.
Improvements:
- Tool Compatibility: Enhanced older custom functions with manually specified descriptions and parameters to align with the updated tool-building system.
Bug Fixes:
- Deep Copy for Ollama Chat Agents: Addressed an issue where manually set clients caused errors during agent model copying, ensuring all properties are properly handled.
What's Changed
- feat: Confluence tool #1334 by @philip-shinra in #1575
- Make confluence cookbook more clear by @dirkbrnd in #1607
- Add a startup idea validator workflow by @dirkbrnd in #1610
- Feat/continue workflow playground by @manthanguptaa in #1552
New Contributors
- @philip-shinra made their first contribution in #1575
Full Changelog: v2.7.4...v2.7.5
Contributors
Assets 2
v2.7.4
This release enhances multimodal capabilities with audio support, improves session page performance, and fixes various bugs for better stability and usability.
New Features
- Audio Response Support: Added support for audio responses, enhancing multimodal interaction capabilities.
- Audio Generation Tools: Integrated Eleven Labs for Audio Generation.
- Cohere Embedder: Introduced a new Cohere Embedder class with a corresponding cookbook example to demonstrate its usage.
- JSON and YAML Agent Storage: Now you can persist your data locally in JSON and YAML extension files
Improvements
- Version Checker for OpenAI: Added a warning for users with OpenAI versions below 1.52.0 to ensure compatibility with features like audio in ChatCompletionMessage.
- Agent Response Handling: Enhanced processing of agent responses to support lists, improving handling of multi-item outputs.
Bug Fixes
- AWS Bedrock Tool Descriptions: Fixed an issue where the transfer tool description was missing, causing incompatibility with AWS Bedrock Claude.
- Response Content Handling: Resolved crashes on the session page caused by non-string response content.
- Deep Copy Agent Memory: Addressed deep copy errors when using agent memory on the playground.
- Session Page Enhancements: Fixed the refresh button
- Fix Tool Parsing for Ollama: Fixed JSON schema tool parsing by transforming ['string', 'null'] parameters to 'string' for compatibility.
- Response Parsing for Gemini Tool: Improved response parsing to handle unserializable objects in tool_calls for Gemini on the playground.
- Memory Handling for Google Provider: Fixed an issue in monitoring_data where memory was removed for all providers, causing blank titles on Phidata.app; now only modifies memory for Google provider.
- RecursiveChunking ID Conflict: Resolved an issue in RecursiveChunking where processing large files with multiple chunks caused duplicate chunk record IDs, leading to psycopg.errors.UniqueViolation.
What's Changed
- created a weekend planner agent by @monali7-d in #1576
- added a book recommendation agent by @monali7-d in #1573
- Added Shopping Partner Agent by @monali7-d in #1571
- Fix: function tools description by @manthanguptaa in #1582
- Add version checker for openai by @dirkbrnd in #1590
- Fix: deep copy agent memory by @manthanguptaa in #1583
- cohere-embedder-phi-2214 by @ysolanky in #1586
- Fix tool parsing for ollama by @dirkbrnd in #1597
- Feat: File Agent Storage by @manthanguptaa in #1596
- Fix response parsing to make gemini tool use work by @dirkbrnd in #1591
- fix: docs has same id with recursive chucking by @cpunion in #1589
- fix-memory-bug-phi-2229 by @ysolanky in #1599
- Multimodal add audio gen tools, eleven labs by @anuragts in #1551
- Fix: path param to dir_path by @manthanguptaa in #1601
- Release 2.7.4 by @dirkbrnd in #1600
New Contributors
- @monali7-d made their first contribution in #1576
- @cpunion made their first contribution in #1589
Full Changelog: v2.7.3...v2.7.4
Contributors
Assets 2
v2.7.3
Changelog
Multi-Modal Tools
This update introduces new multimodal tools, enhances the multimodal capabilities of existing models, and includes several quality-of-life improvements.
New Features
Giphy Tool: Added Giphy integration to enhance creative collaboration.
Native image upload support for Claude: Added native support for uploading images natively to the Anthropic API.
Youtube Knowledge base: Added support for new YouTube knowledge base, allowing it to be loaded directly using YouTube video links.
Improvements
API key validation: Added API key validation for model classes.
Gemini audio: Improved native audio upload support for Gemini Model.
YoutubeTools: A new Youtube tool which allows generation of timestamps
Workspace Configuration Flexibility: Refactored type-checking logic using isinstance() to enhance flexibility and maintainability.
Web Crawler Stability: Switched to crawl4ai async to resolve issues and improve performance.
Memory Optimization: Improved memory usage in large-scale workflows for better efficiency.
User Interface: Refined the UI for better tracking of team activities.
Bug Fixes
Role-Based Access Control Bugs: Resolved issues affecting access permissions.
Gemini Functions: Fixed errors when functions had no specified parameters.
What's Changed
- Gemini audio fix phi 2202 by @ysolanky in #1557
- generates timestamp of a youtube video by @pritipsingh in #1559
- Use Case : Study Partner by @unnati914 in #1529
- Add chromadb vectordb cookbook by @manthanguptaa in #1560
- Fix issue with gemini functions with no parameters by @dirkbrnd in #1562
- updated stale issues action to v9 by @Ansub in #1453
- Feat: Youtube Knowledge Base Video URLs by @lucifertrj in #1545
- Switch to crawl4ai async to fix issues with webcrawler by @dirkbrnd in #1563
- claude-image-support-phi-2207 by @ysolanky in #1566
- Youtubetools proxy param phi 2208 by @ysolanky in #1568
- Refactor: Use isinstance() for type checking to enhance flexibility i… by @alphamarket in #1490
- Add giphy tool [PHI-2206] by @dirkbrnd in #1565
- Add key validation on all models by @dirkbrnd in #1578
New Contributors
- @alphamarket made their first contribution in #1490
Full Changelog: v2.7.2...v2.7.3
Contributors
Assets 2
v2.7.2
v2.7.1
Changelog
New Features
Gemini Multimodal Support: Added support for multimodal (image, video, text) input processing with Gemini.
Mem0 Integration Example: Introduced a cookbook example demonstrating Mem0 integration for Agent memory.
CSV URL Knowledgebase: Added functionality to create and manage knowledgebases from CSV URLs.
Improvements
Vertex AI Gemini 2 Update: The Vertex AI class has been updated to support the Gemini 2 model
Bug Fixes
Structured Output Fix: Resolved issues with Ollama structured output to ensure consistent data formatting.
What's Changed
- vertex-ai-gemini-2-update-phi-2172 by @ysolanky in #1549
- Feat: CSV Url Knowledgebase by @manthanguptaa in #1543
- mem0-integration-phi-2157 by @ysolanky in #1542
- Gemini multimodality update phi 2173 by @ysolanky in #1548
- ollama-structured-output-fix-phi-2164 by @ysolanky in #1547
Full Changelog: v2.7.0...v2.7.1
Contributors
Assets 2
v2.7.0
This update introduces image and video multi-modal support for the agent playground and adds image and video generation tools like FAL, replicate, and ModelLabs.
Highlights
- Support for video: Agents now natively support video
- Multi-Modal rendering on Agent Playground: Agent Playground can now render images and videos
New Feature
- New Tools: Added Replicate, FAL, and ModelLabs tools to generate video and images
Improvements
- Various cookbook examples were added to cover real-world agent use cases
New Contributors
- @dirkbrnd made their first contribution in #1531
- @unnati914 made their first contribution in #1511
- @saajann made their first contribution in #1538
Full Changelog: v2.6.7...v2.7.0
Contributors
Assets 2
v2.6.7
Contributors
Assets 2
v2.6.6
Full Changelog: v2.6.5...v2.6.6