Product updates
1.1.0 - Models Refactor and Cloud Support
Model Improvements:
- Models Refactor: A complete overhaul of our models implementation to improve on performance and to have better feature parity across models.
- This improves metrics and visibility on the Agent UI as well.
- All models now support async-await, with the exception of
AwsBedrock
.
- Azure AI Foundry: We now support all models on Azure AI Foundry. Learn more here..
- AWS Bedrock Support: Our redone AWS Bedrock implementation now supports all Bedrock models. It is important to note which models support which features.
- Gemini via Google SDK: With the 1.0.0 release of Google’s genai SDK we could improve our previous implementation of
Gemini
. This will allow for easier integration of Gemini features in future. - Model Failure Retries: We added better error handling of third-party errors (e.g. Rate-Limit errors) and the agent will now optionally retry with exponential backoff if
exponential_backoff
is set toTrue
.
Other Improvements
- Exa Answers Support: Added support for the Exa answers capability.
- GoogleSearchTools: Updated the name of
GoogleSearch
toGoogleSearchTools
for consistency.
Deprecation
- Our
Gemini
implementation directly on the Vertex API has been replaced by the Google SDK implementation ofGemini
. - Our
Gemini
implementation via the OpenAI client has been replaced by the Google SDK implementation ofGemini
. - Our
OllamaHermes
has been removed as the implementation ofOllama
was improved.
Bug Fixes
- Team Members Names: Fixed a bug where teams where team members have non-aphanumeric characters in their names would cause exceptions.
1.0.8
New Features:
- Perplexity Model: We now support Perplexity 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.
1.0.7
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()
andagent.aprint_response()
. - Cohere Async: Cohere now supports async execution via
agent.arun()
andagent.aprint_response()
.
Bug Fixes:
- Retriever as knowledge source: Added small fix and examples for using the custom
retriever
parameter with an agent.
1.0.6
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.
1.0.5
New Features:
- Gmail Tools: Add tools for Gmail, including mail search, sending mails, etc.
Improvements:
- Exa Toolkit Upgrade: Added
find_similar
toExaTools
- Claude Async: Claude models can now be used with
await agent.aprint_response()
andawait agent.arun()
. - Mistral Vision: Mistral vision models are now supported. Various examples were added to illustrate example.
1.0.4
Bug Fixes:
- Claude Tool Invocation: Fixed issue where Claude was not working with tools that have no parameters.
1.0.3
Improvements:
- OpenAI Reasoning Parameter: Added a reasoning parameter to OpenAI models.
1.0.2
Improvements:
- Model Client Caching: Made all models cache the client instantiation, improving Agno agent instantiation time
- XTools: Renamed
TwitterTools
toXTools
and updated capabilities to be compatible with Twitter API v2.
Bug Fixes:
- Agent Dataclass Compatibility: Removed
slots=True
from the agent dataclass decorator, which was not compatible with Python < 3.10. - AzureOpenAIEmbedder: Made
AzureOpenAIEmbedder
a dataclass to match other embedders.
1.0.1
Improvement:
- Mistral Model Caching: Enabled caching for Mistral models.
1.0.0 - Agno
This is the major refactor from phidata
to agno
, released with the official launch of Agno AI.
See the migration guide for additional guidance.
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=[])
andagent.print_response(images=[])
is now of typeImage
-
agent.run(audio=[])
andagent.print_response(audio=[])
is now of typeAudio
-
agent.run(video=[])
andagent.print_response(video=[])
is now of typeVideo
-
RunResponse.images
is now a list of typeImageArtifact
-
RunResponse.audio
is now a list of typeAudioArtifact
-
RunResponse.videos
is now a list of typeVideoArtifact
-
RunResponse.response_audio
is now of typeAudioOutput
-
-
Models:
Hermes
→OllamaHermes
AzureOpenAIChat
→AzureOpenAI
CohereChat
→Cohere
DeepSeekChat
→DeepSeek
GeminiOpenAIChat
→GeminiOpenAI
HuggingFaceChat
→HuggingFace
-
Embedders now all take
id
instead ofmodel
as a parameter. For example -
Agent Storage class
PgAgentStorage
→PostgresDbAgentStorage
SqlAgentStorage
→SqliteDbAgentStorage
MongoAgentStorage
→MongoDbAgentStorage
S2AgentStorage
→SingleStoreDbAgentStorage
-
Workflow Storage class
SqlWorkflowStorage
→SqliteDbWorkflowStorage
PgWorkflowStorage
→PostgresDbWorkflowStorage
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.
- Moved
Embedder
class from pydantic to data class
Removals
- Removed all references to
Assistant
- Removed all references to
llm
- Removed the
PhiTools
tool - On the
Agent
class,guidelines
,prevent_hallucinations
,prevent_prompt_leakage
,limit_tool_access
, andtask
has been removed. They can be incorporated into theinstructions
parameter as you see fit.
Bug Fixes:
- Semantic Chunking: Fixed semantic chunking by replacing
similarity_threshold
param withthreshold
param.
New Features:
- Evals for Agents: Introducing Evals to measure the performance, accuracy, and reliability of your Agents.