v1.0.8

Changelog

New Features:

• Perplexity Model: We now support [Perplexity](https://www.perplexity.ai/) as a model provider.
• Todoist Toolkit: Added a toolkit for managing tasks on Todoist.
• JSON Reader: Added a JSON file reader for use in knowledge bases.

Improvements:

• LanceDb: Implemented name_exists function for LanceDb

Bug Fixes:

• Storage growth bug: Fixed a bug with duplication of run_messages.messages for every run in storage

What's Changed

• Mistral Async implementation by @dirkbrnd in #2002
• Async Cohere by @manthanguptaa in #2004
• Google sheets tool ag 2636 by @ysolanky in #1994
• weaviate-vector-db-ag-2637 by @ysolanky in #1995
• Add custom retriever by @ashpreetbedi in #2013
• fix: chess readme env by @anuragts in #2016
• Added Todoist Tool by @Ansub in #2020
• Update cookbooks to composio agno by @dirkbrnd in #2033
• Add JSON file support for file input by @pritipsingh in #2009
• lance-db-name_exists-ag-2655 by @ysolanky in #2024
• AG-2323 Add perplexity model by @willemcdejongh in #1997
• add image support in file upload by @Ayush0054 in #2007
• fix-memory-ag-2662 by @ysolanky in #2028
• Add logging for various operations in tools by @onukura in #2011
• Run response default dict fix by @dirkbrnd in #2034
• fix: pineconedb use namespace value from global variable by @leontruzqy in #2041
• Make email param optional in cal tool by @srexrg in #1970
• Release 1.0.8 by @dirkbrnd in #2043

New Contributors

• @onukura made their first contribution in #2011
• @leontruzqy made their first contribution in #2041

Full Changelog: v1.0.6...v1.0.8

v1.0.7

Changelog

New Features:

• Google Sheets Toolkit: Added a basic toolkit for reading, creating and updating Google sheets.
• Weviate Vector Store: Added support for Weviate as a vector store.

Improvements:

• Mistral Async: Mistral now supports async execution via agent.arun() and agent.aprint_response().
• Cohere Async: Cohere now supports async execution via agent.arun() and agent.aprint_response()

Bug Fixes:

• Retriever as knowledge source: Added small fix and examples for using the custom retriever parameter with an agent.

What's Changed

• Mistral Async implementation by @dirkbrnd in #2002
• Async Cohere by @manthanguptaa in #2004
• Google sheets tool ag 2636 by @ysolanky in #1994
• weaviate-vector-db-ag-2637 by @ysolanky in #1995
• Add custom retriever by @ashpreetbedi in #2013
• fix: chess readme env by @anuragts in #2016

Full Changelog: v1.0.6...v1.0.7

v1.0.6

Changelog

New Features:

• Google Maps Toolkit: Added a rich toolkit for Google Maps that includes business discovery, directions, navigation, geocode locations, nearby places, etc.
• URL reader and knowledge base: Added reader and knowledge base that can process any URL and store the text contents in the document store.

Bug Fixes:

• Zoom tools fix: Zoom tools updated to include the auth step and other misc fixes.
• Github search_repositories pagination: Pagination did not work correctly and this was fixed.

What's Changed

• Fix implementation of zoom tools by @dirkbrnd in #1986
• Fix pagination in github tools and add tests by @dirkbrnd in #1996
• Add google maps toolkit [AG-2575] by @dirkbrnd in #1962
• Update performance evals for other frameworks by @dirkbrnd in #2006
• Deep knowledge by @ashpreetbedi in #2010

Full Changelog: v1.0.5...v1.0.6

v1.0.5

Changelog

New Features:

• Gmail Tools: Add tools for Gmail, including mail search, sending mails, etc.

Improvements:

• Exa Toolkit Upgrade: Added find_similar to ExaTools
• Claude Async: Claude models can now be used with await agent.aprint_response() and await agent.arun().
• Mistral Vision: Mistral vision models are now supported. Various examples were added to illustrate.

What's Changed

• Updates CONTRIBUTING.md to add installation of uv in development setup by @Harsh-2909 in #1971
• Expand Exa capabilities by @dirkbrnd in #1888
• Claude Async with async tool calls by @dirkbrnd in #1984
• Mistral vision support by @dirkbrnd in #1956
• Add gmail toolkit [AG-2574] by @dirkbrnd in #1961
• o3-mini reasoning effort example by @Ayush0054 in #1991
• Release 1.0.5 by @dirkbrnd in #1989

New Contributors

• @Harsh-2909 made their first contribution in #1971

Full Changelog: v1.0.4...v1.0.5

v1.0.4

Changelog

Bug Fixes:

• Fixed a bug with Claude not working with tools that have no params

What's Changed

• remove use-tools param by @Ayush0054 in #1969
• fix: change model to o3-mini by @anuragts in #1973
• Infra dependencies ag 2568 by @ysolanky in #1951
• claude-bug-fix-ag-2579 by @ysolanky in #1979

Full Changelog: v1.0.3...v1.0.4

v1.0.3

What's Changed

• Add reasoning param by @ashpreetbedi in #1964

Full Changelog: v1.0.2...v1.0.3

v1.0.2

Changelog

Improvements:

• Model Client Caching: Made all models cache the client instantiation, improving Agno agent instantiation time
• XTools: Renamed TwitterTools to XTools and updated capabilities to be compatible with Twitter API v2.

Bug Fixes:

• Removed slots=true from the agent dataclass decorator which was not compatible with Python <3.10
• Fixed issue with AzureOpenAIEmbedder not being correctly made a dataclass

What's Changed

• Update issue templates by @ysolanky in #1950
• Remove slots from the Agent class by @ashpreetbedi in #1957
• Rename twitter toolkit. by @dirkbrnd in #1926
• Fix azure embedder by @manthanguptaa in #1959
• Cache model clients by @ashpreetbedi in #1949
• Release 1.0.2 by @dirkbrnd in #1960

Full Changelog: v1.0.1...v1.0.2

v1.0.1

Changelog

Improvements:

• Enabled caching for Mistral models.

What's Changed

• Cache mistral models by @ashpreetbedi in #1948

Full Changelog: v1.0.0...v1.0.1

v1.0.0

Changelog

This is a major refactor to be coupled with the launch of Agno.

Interface Changes:

• phi.model.x → agno.models.x

• phi.knowledge_base.x → agno.knowledge.x (applies to all knowledge bases)

• phi.document.reader.xxx → agno.document.reader.xxx_reader (applies to all document readers)

• All Agno toolkits are now suffixed with Tools. E.g. DuckDuckGo → DuckDuckGoTools

• Multi-modal interface updates:

  • agent.run(images=[]) and agent.print_response(images=[]) is now of type Image

    class Image(BaseModel):
        url: Optional[str] = None  # Remote location for image
        filepath: Optional[Union[Path, str]] = None  # Absolute local location for image
        content: Optional[Any] = None  # Actual image bytes content
        detail: Optional[str] = None # low, medium, high or auto (per OpenAI spec https://platform.openai.com/docs/guides/vision?lang=node#low-or-high-fidelity-image-understanding) 
        id: Optional[str] = None

  • agent.run(audio=[]) and agent.print_response(audio=[]) is now of type Audio

    class Audio(BaseModel):
        filepath: Optional[Union[Path, str]] = None  # Absolute local location for audio
        content: Optional[Any] = None  # Actual audio bytes content
        format: Optional[str] = None

  • agent.run(video=[]) and agent.print_response(video=[]) is now of type Video

    class Video(BaseModel):
        filepath: Optional[Union[Path, str]] = None  # Absolute local location for video
        content: Optional[Any] = None  # Actual video bytes content

  • RunResponse.images is now a list of type ImageArtifact

    class ImageArtifact(Media):
        id: str
        url: str  # Remote location for file
        alt_text: Optional[str] = None

  • RunResponse.audio is now a list of type AudioArtifact

    class AudioArtifact(Media):
        id: str
        url: Optional[str] = None  # Remote location for file
        base64_audio: Optional[str] = None  # Base64-encoded audio data
        length: Optional[str] = None
        mime_type: Optional[str] = None

  • RunResponse.videos is now a list of type VideoArtifact

    class VideoArtifact(Media):
        id: str
        url: str  # Remote location for file
        eta: Optional[str] = None
        length: Optional[str] = None

  • RunResponse.response_audio is now of type AudioOutput

    class AudioOutput(BaseModel):
        id: str
        content: str  # Base64 encoded
        expires_at: int
        transcript: str

• Models:

  • Hermes → OllamaHermes
  • AzureOpenAIChat → AzureOpenAI
  • CohereChat → Cohere
  • DeepSeekChat → DeepSeek
  • GeminiOpenAIChat → GeminiOpenAI
  • HuggingFaceChat → HuggingFace

• Embedders now all take id instead of model as a parameter. For example

  db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
  
  knowledge_base = PDFUrlKnowledgeBase(
      urls=["https://phi-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
      vector_db=PgVector(
          table_name="recipes",
          db_url=db_url,
          embedder=OllamaEmbedder(id="llama3.2", dimensions=3072),
      ),
  )
  knowledge_base.load(recreate=True)

• Agent Storage class

  • PgAgentStorage → PostgresAgentStorage
  • SqlAgentStorage → SqliteAgentStorage
  • MongoAgentStorage → MongoDbAgentStorage
  • S2AgentStorage → SingleStoreAgentStorage

• Workflow Storage class

  • SqlWorkflowStorage → SqliteWorkflowStorage
  • PgWorkflowStorage → PostgresWorkflowStorage
  • MongoWorkflowStorage → MongoDbWorkflowStorage

• Knowledge Base

  • phi.knowledge.pdf.PDFUrlKnowledgeBase → agno.knowledge.pdf_url.PDFUrlKnowledgeBase
  • phi.knowledge.csv.CSVUrlKnowledgeBase → agno.knowledge.csv_url.CSVUrlKnowledgeBase

• Readers

  • phi.document.reader.arxiv → agno.document.reader.arxiv_reader
  • phi.document.reader.docx → agno.document.reader.docx_reader
  • phi.document.reader.json → agno.document.reader.json_reader
  • phi.document.reader.pdf → agno.document.reader.pdf_reader
  • phi.document.reader.s3.pdf → agno.document.reader.s3.pdf_reader
  • phi.document.reader.s3.text → agno.document.reader.s3.text_reader
  • phi.document.reader.text → agno.document.reader.text_reader
  • phi.document.reader.website → agno.document.reader.website_reader

Improvements:

• Dataclasses - Changed various instances of Pydantic models to dataclasses to improve the speed.

Removals

• Removed all references to Assistant
• Removed all references to llm
• Removed the PhiTools tool
• Removed the PythonAgent and DuckDbAgent (this will be brought back in future with more specific agents)

Bug Fixes:

• Fixed semantic chunking by replacing similarity_threshold param with threshold param

New Features

• Introducing Evals to measure the performance, accuracy, and reliability of your Agents