NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI · #3100 most downloaded on PyPI
The programming language for agentic software.
Last release 4 days ago
16 Sep 2026
Ships on a steady schedule
a new release about every 9 days
Nearly every release is documented
notes for 59 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
2 years old
263 releases · first in 2024
One column per month.
New Streaming Events: We have improved our streaming events system. See the details in “breaking changes” section at the bottom.
RunResponse now does not have an event attribute. It still represents the responses of the entire run.RunResponse.status now indicates whether the run response is RUNNING, PAUSED, or CANCELLED.agent.run(..., stream=True) or agent.arun(..., stream=True) .RunResponseContentRunErrorRunCancelledToolCallStartedToolCallCompletedstream_intermediate_steps=True:
RunStartedRunCompletedReasoningStartedReasoningStepReasoningCompletedMemoryUpdateStartedMemoryUpdateCompletedTeamRunResponseContentTeamRunErrorTeamRunCancelledTeamToolCallStartedTeamToolCallCompletedstream_intermediate_steps=True:
TeamRunStartedTeamRunCompletedTeamReasoningStartedTeamReasoningStepTeamReasoningCompletedTeamMemoryUpdateStartedTeamMemoryUpdateCompletedWorkflowRunResponseStartedEvent and WorkflowRunResponseCompletedEvent events.Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.10...v1.6.0
Playground File Upload: We now support file upload via the Agno Playground. This will send PDF, CSV, Docx, etc files directly to the agents/teams for
research tool on ExaTools. See more on their docs about how their research works.Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.9...v1.5.10
ZepTools Updates: Updated ZepTools to remove deprecated features.
SerperTools toolkit to search GooglePDFBytesKnowledgeBase, which allows the ingestion of in-memory PDF content via bytes or IO streams instead of file paths.DaytonaTools toolkit to let Agents execute code remotely on Daytona sandboxesAWSSESTools to send emails via AWS SES.add_location_to_instructions to automatically detect the current location where the agent is running and add that to the system message.agent was replaced with agents, team with teams and workflows was added. This also now requires you to specify which agent/team/workflow to run.
http://localhost:8001/runs?agent_id=my-agentZepTools to remove deprecated features.GmailTools now support attachments.fetch_with_retry and async_fetc_with_retry to be reused inurl_reader.pysearch_posts for XTools.slack, whatsapp, etcRunResponse.to_dict() to handle non-serializable fields, as Python enumsFull Changelog: https://github.com/agno-agi/agno/compare/v1.5.8...v1.5.9
Slack App: Introducing the SlackApp to allow you to create agents for Slack! The app allows agents to respond to individual messages or on group chats
SlackApp to allow you to create agents for Slack! The app allows agents to respond to individual messages or on group chats, and it creates threads to respond to messages.VisualizationTools that uses matplotlib to give agents the ability to make graphs.BraveSearch that allows agent to search the web using brave search api.knowledge_filters even if self.add_references=True which is a case for traditional RAG (diff from Agentic RAG)Mem0ToolsSearxng tool initialization: Fixed Searxng tool initialization error
AttributeError: 'Searxng' object has no attribute 'include_tools'
and added comprehensive unit tests.
Fix for enum as a response model for Gemini: With 1.5.6, a bug was introduced now allowing enum as a data type for Gemini response model.
OpenAI parsing structured output: With the changes in the OpenAI library we don't need to parse the structured output separately.
Fix accuracy evals monitoring: Added logic to handle monitoring when evaluating Teams in the run function of AccuracyEval
FastAPIApp does not have a default prefix anymore and /run → /runs (i.e. the created run endpoint is now <your_domain>/runs)serve_fastapi_app is now replaced with .serve() on the instance of FastAPIApp.serve_whatsapp_app is now replaced with .serve() on the instance of WhatsappAPI.Team Evals: Evaluations are now supported for teams!
arun support for Workflows, so they can now be used with async Python.tool_call_limit: Revamp of tool_call_limit to make it work across a whole agent run.run.team_session_state is now correctly propagated and shared between all members and sub-teams of a team.Dict[str, int] fields (and other Dict types) were failing when used as response_schema for both OpenAI and Gemini models due to schema format incompatibilities.session_name is now available after a run.team_session_state, you now have to set team_session_state on the Team instead of session_state.Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.5...v1.5.6
chore: update qdrant to remove hybrid search breaking change by @kausmeows in https://github.com/agno-agi/agno/pull/3360
AI/ML API, a platform providing AI/ML models. AI/ML API provides 300+ AI models including Deepseek, Gemini, ChatGPT. The models run at enterprise-grade rate limits and uptimes.Pydantic and dataclass objects as input to a function. See here for an example.concurrent.futures module to enforce timeouts on all Exa API operations (search, get contents, find similar, and answer generation).get_previous_session_messages(number_of_sessions: int) that returns a list of messages that the agent can analysesearch_previous_sessions_historyexpire key to set TTL on Redis keys.cache_creation_input_tokens to agent session metrics, to allow for tracking Anthropic cache write statistics.post on their InferenceClient()- https://discuss.huggingface.co/t/getting-error-attributeerror-inferenceclient-object-has-no-attribute-post/156682id: str = "jinaai/jina-embeddings-v2-base-code" as default, because these models are no longer provided by the HF Inference API. Changed the default to id: str = "intfloat/multilingual-e5-large"role_map for OpenAIChat: This allows certain models that don’t adhere to OpenAI’s role mapping to be used vir OpenAILike.content_hash in upsert as ID.Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.4...v1.5.5
User Control Flows: This is the beta release of Agno’s Human-in-the-loop flows and tools.
paused awaiting completion of certain user requirements before the agent can continue.agent.continue_run and agent.acontinue_run functions.@tool(requires_confirmation=True) and the agent will expect user confirmation before executing the tool.@tool(requires_user_input=True) to have the agent stop and ask for user input before continuing.@tool(external_execution=True) to indicate that you will execute this function outside of the agent context.UserControlFlowTools() to an agent to give the agent the ability to dynamically stop the flow and ask for user input where required.FirecrawlTools.include_tools and exclude_tools.Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.3...v1.5.4
Improved Accuracy Evals: Updated the way accuracy evals works for more accurate agent-based evaluation.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.2...v1.5.3
Agno Apps (Beta): Introducing Agno Apps, convenience functions to assist with building production-ready applications. The first supported apps are:
FastAPIApp → A really simple FastAPI server that provides access to your agent or team.WhatsappAPIApp → An app that implements the Whatsapp protocol allowing you to have an Agno agent running on Whatsapp. Supports image / audio / video input and can generate images as responses. Supports reasoning.cosmos_compatibility=Truepdf and text s3 readers.stop_after_tool_call and show_result for Toolkits: Now the base Toolkit class has stop_after_tool_call_tools and show_result_tools similar to the @tool decorator.WebsiteReader._extract_main_content by 72% by @misrasaurabh1 in https://github.com/agno-agi/agno/pull/3013Full Changelog: https://github.com/agno-agi/agno/compare/v1.5.1...v1.5.2
Nebius Model Provider: Added Nebius as a model provider.
ssl parameter to Redis storage.Full Changelog: https://github.com/agno-agi/agno/compare/v.1.5.0...v1.5.1
Azure OpenAI Tools: Added image generation via Dall-E via Azure AI Foundry.
hybrid_search on Milvus.PerfEval to PerformanceEvalagent, prompt and expected_answerstream=True). Individual events will have more relevant data now.Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.6...v1.5.0
Azure OpenAI Tools: Added image generation via Dall-E via Azure AI Foundry.
hybrid_search on Milvus.PerfEval to PerformanceEvalagent, prompt and expected_answerstream=True). Individual events will have more relevant data now.Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.6...v1.5.0
Cerebras Model Provider: Added Cerebras as a model provider.
Two Ways to Apply Filters:
Explicit Filtering: Pass filters directly to Agent or during run/query
# Option 1: Filters on Agent initialization
agent = Agent(
knowledge=knowledge_base,
knowledge_filters={"filter_1": "abc"}
)
# Option 2: Filters on run execution
agent.run("Tell me about...", knowledge_filters={"filter_1": "abc"})
See docs here
Agentic Filtering: Agent automatically detects and applies filters from user queries
# Enable automatic filter detection
agent = Agent(
knowledge=knowledge_base,
enable_agentic_knowledge_filters=True
)
# Agent extracts filters from query
agent.run("Tell me about John Doe's experience...")
See docs here
Two approaches for adding metadata to documents:
During Knowledge Base Initialization:
knowledge_base = PDFKnowledgeBase(path=[
{
"path": "file_1.pdf",
"metadata": {
"user_id": "abc"
}
},
{
"path": "file_2.pdf",
"metadata": {
"user_id": "xyz"
}
}
])
During Individual Document Loading:
knowledge_base.load_document(
path="file.pdf",
metadata={"user_id": "abc"}
)
Compatibility
PDF, Text, DOCX, JSON, and PDF_URLQdrant, LanceDB, and MongoDBcurrent_user_id and current_session_id as default variables in session_data.abc.-.xyz.pdf and abc.-.def.pdf) were being incorrectly identified due to the readers using formatted names as unique id which were getting uniqueness conflict. Introduced a unique ID for each document in all the readers using uuidv4() to ensure strict identification and prevent conflicts.Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.5...v1.4.6
Embedder Support via AWS Bedrock: AwsBedrockEmbedder has been added with a default embedding model of cohere.embed-multilingual-v3.
AwsBedrockEmbedder has been added with a default embedding model of cohere.embed-multilingual-v3.GeminiTools.ApifyTools to make it completely compatible with Apify actors.Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.4...v1.4.5
OpenAI File Support: Added support for File attached to prompts for agents with OpenAIChat models.
File attached to prompts for agents with OpenAIChat models.retriever parameter can now be an async function to be used with agent.arun and agent.aprint_response.Video(url=...) for Gemini.OpenAIResponses.MCPTools usage while calling agent.acli_app.request_params to Bedrock Converse API by @leandrodamascena in https://github.com/agno-agi/agno/pull/3035Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.3...v1.4.4
Llama API: Added native SDK and OpenAI-like model classes.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.2...v1.4.3
MCP SSE Support: Added support for connecting to SSE MCP Servers.
Toolkits and custom tools. See this example.PubmedTools .Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.1...v1.4.2
chore(playground): cookbook showing an agent with structured outputs in the playground by @manuhortet in https://github.com/agno-agi/agno/pull/2942
Full Changelog: https://github.com/agno-agi/agno/compare/v1.4.0...v1.4.1
Memory: Agents will now by default use an improved Memory instead of the now deprecated AgentMemory.
OpenAITools to enable text-to-speech and image generation through OpenAI’s APIs.ZepTools and AsyncZepTools to manage memories for your Agent using zep-cloudinclude_tools and exclude_tools for all toolkits. This allows for selective enabling / disabling of tools inside toolkits, which is especially useful for larger toolkits.deepcopy when Gemini is used with Memory.Memory instead of the now deprecated AgentMemory.
agent.memory.messages → run.messages for run in agent.memory.runs (or agent.get_messages_for_session())create_user_memories → enable_user_memories and is now set on the Agent/Team directly.create_session_summary → enable_session_summaries and is now set on the Agent/Team directly.Full Changelog: https://github.com/agno-agi/agno/compare/v1.3.5...v1.4.0
Further Async Vector DB Support: Support added for:
reasoning_content on RunResponse for stream/non-stream, async/non-asyncReasoning eventsdoc_id before inserting by @alpha-xone in https://github.com/agno-agi/agno/pull/2685Full Changelog: https://github.com/agno-agi/agno/compare/v1.3.4...v1.3.5
insert/upsert/log_info only if there are documents from reader by @5739n4 in https://github.com/agno-agi/agno/pull/2869
client_params arg by @skiran252 in https://github.com/agno-agi/agno/pull/2764Full Changelog: https://github.com/agno-agi/agno/compare/v1.3.3...v1.3.4
Gemini File Upload: Enabled direct use of uploaded files with Gemini.
apprint_run_response to support async.Full Changelog: https://github.com/agno-agi/agno/compare/v.1.3.2...v1.3.3
Redis Memory DB: Added Redis as a storage provider for Memory. See here.
Memory. See here.agent.get_session_summary() → Use to get the previous session summary from the agent.agent.get_user_memories() → Use to get the current user’s memories.MemoryManager or SessionSummarizer.add_member_tools_to_system_message to remove the member tool names from the system message given to the team leader, which allows flexibility to make teams transfer functions work in more cases.Full Changelog: https://github.com/agno-agi/agno/compare/v1.3.1...v.1.3.2
Update reasoning cookbooks link by @ravi03071991 in https://github.com/agno-agi/agno/pull/2807
Full Changelog: https://github.com/agno-agi/agno/compare/v1.3.0...v1.3.1
Memory Revamp (beta): Releasing a complete revamp of Agno Memory (beta release). This includes a new Memory class that supports adding, updating and d
Memory class that supports adding, updating and deleting user memories, as well as doing semantic search with a model. This also adds additional abilities to the agent to manage memories on your behalf. See the docs here.user_id and session_id on agent.run(). This will ensure the agent is set up for the session belonging to the session_id and that only the memories of the current user is accessible to the agent. This allows you to build multi-user and multi-session applications with a single agent configuration.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.16...v1.3.0
Teams Improvements: Multiple improvements to teams to make task forwarding to member agents more reliable and to make the team leader more conversatio
knowledge to Team to better align with the functionality on Agent. This comes with retriever to set a custom retriever and search_knowledge to enable Agentic RAG.OpenAIResponses and OpenAIChat.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.15...v1.2.16
Update: SQL Agent by @ashpreetbedi in https://github.com/agno-agi/agno/pull/2734
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.14...v1.2.15
Improved Github Tools: Added many more capabilities to GithubTools.
GithubTools.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.13...v1.2.14
v1.2.13 by @ashpreetbedi in https://github.com/agno-agi/agno/pull/2719
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.12...v1.2.13
Timezone Identifier: Added a new timezone_identifier parameter in the Agent class to include the timezone alongside the current date in the instructio
timezone_identifier parameter in the Agent class to include the timezone alongside the current date in the instructions.ReasoningTools for an advanced reasoning scratchpad for agents.async-await support:
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.11...v1.2.12
Fix for structured outputs: Fixed cases of structured outputs for reasoning.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.10...v1.2.11
Knowledge Tools: Added KnowledgeTools for thinking, searching and analysing documents in a knowledge base.
KnowledgeTools for thinking, searching and analysing documents in a knowledge base.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.9...v1.2.10
Simpler MCP Interface: Added MultiMCPTools to support multiple server connections and simplified the interface to only allow command to be passed. See
MultiMCPTools to support multiple server connections and simplified the interface to only allow command to be passed. See these examples of how to use it. See the updated docs.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.8...v1.2.9
Toolkit Instructions: Extended Toolkit with instructions and add_instructions to enable you to specify additional instructions related to how a tool s
Toolkit with instructions and add_instructions to enable you to specify additional instructions related to how a tool should be used. These instructions are then added to the model’s “system message” if add_instructions=True .Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.7...v1.2.8
Created: March 31, 2025 4:13 PM
Created: March 31, 2025 4:13 PM
gemini-2.0-flash-exp-image-generation model.@tool decorator. See the docs here.async-await support, so it will be used in agent.arun and agent.aprint_response. This also means that knowledge_base.aload() is possible which should greatly increase loading speed in some cases. The following have been converted:
JSONKnowledgeBase → Here is a cookbook to illustrate how to use it.PDFKnowledgeBase → Here is a cookbook to illustrate how to use it.PDFUrlKnowledgeBase → Here is a cookbook to illustrate how to use it.CSVKnowledgeBase → Here is a cookbook to illustrate how to use it.CSVUrlKnowledgeBase → Here is a cookbook to illustrate how to use it.ArxivKnowledgeBase → Here is a cookbook to illustrate how to use it.WebsiteKnowledgeBase → Here is a cookbook to illustrate how to use it.YoutubeKnowledgeBase → Here is a cookbook to illustrate how to use it.TextKnowledgeBase → Here is a cookbook to illustrate how to use it.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.6...v1.2.7
Gemini Function call result fix: Fixed a bug with function call results failing formatting and added proper role mapping
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.5...v1.2.6
E2B Tools: Added E2B Tools to run code in E2B Sandbox
tools and tool_call_limit to Team. This means the team leader itself can also have tools provided by the user, so it can act as an agent.MCPTools to allow you to specify tools to specifically include or exclude from all the available tools on an MCP server. This is very useful for limiting which tools the model has access to.@tool() decorator now supports async functions, including async pre and post-hooks.tool_choice from Ollama usage as it is not supported.entity_id mappingsFull Changelog: https://github.com/agno-agi/agno/compare/v1.2.4...v1.2.5
Tool Choice on Teams: Made tool_choice configurable.
tool_choice configurable.update_task on TodoistTools.Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.3...v1.2.4
Teams Error Handling: Improved the flow in cases where the model gets it wrong when forwarding tasks to members.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.2...v1.2.3
Teams Memory: Fixed issues related to memory not persisting correctly across multiple sessions.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.1...v1.2.2
Teams Markdown: Fixed issue with markdown in teams responses.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.2.0...v1.2.1
Add fallback to deprecated imghdr by @Sebastiao-Assuncao in https://github.com/agno-agi/agno/pull/2487
MCPTools for connections to external MCP servers. See the updated docs.Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.17...v1.2.0
Better Debug Logs: Enhanced debug logs for better readability and clarity.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.16...v1.1.17
Async Qdrant VectorDB: Implemented async support for Qdrant VectorDB, improving performance and efficiency.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.15...v1.1.16
Function Result Caching: Added caching of selected searchers and scrapers. This is only intended for testing and should greatly improve iteration spee
print_response and aprint_response is used. They are now displayed in a separate panel different from response panel. It can also be used in conjunction in response_model.Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.14...v1.1.15
Support for Agent(team=[]) is still there, but deprecated (see below).
Team in one of 3 modes: “Collaborate”, “Coordinate” or “Route”.debug_mode=True and team.print_response(...) to see it in action.Agent(team=[]) is still there, but deprecated (see below).OpenAILike interface.use_json_mode: bool = False as a parameter of Agent and Team, which in conjunction with response_model=YourModel, is used to indicate whether the agent/team model should be forced to respond in json instead of (now default) structured output. Previous behaviour defaulted to “json-mode”, but since most models now support native structured output, we are now defaulting to native structured output. It is now also much simpler to work with response models, since now only response_model needs to be set. It is not necessary anymore to set structured_output=True to specifically get structured output from the model.WebsiteTools to also update combined knowledgebases.get_message_pairs() fetching incorrect messages.Agent.structured_output has been replaced by Agent.use_json_mode. This will be removed in a future major version release.Agent.team is deprecated with the release of our new Teams implementation. This will be removed in a future major version release.Full Changelog: https://github.com/agno-agi/agno/compare/v.1.1.13...v1.1.14
OpenAIResponses File Search: Added support for the built-in “File Search” function from OpenAI. This automatically uploads File objects attached to th
File objects attached to the agent prompt.File objects are attached to agent prompts.Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.12...v.1.1.13
Citations: Improved support for capturing, displaying, and storing citations from models, with integration for Gemini and Perplexity.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.11...v1.1.12
OpenAI Responses: Added a new model implementation that supports OpenAI’s Responses API. This includes support for their “websearch” built-in tool.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.10...v1.1.11
File Prompts: Introduced a new File type that can be added to prompts and will be sent to the model providers. Only Gemini and Anthropic Claude suppor
File type that can be added to prompts and will be sent to the model providers. Only Gemini and Anthropic Claude supported for now.Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.9...v1.1.10
IBM Watson X: Added support for IBM Watson X as a model provider. Find the docs here.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.8...v1.1.9
Video File Upload on Playground: You can now upload video files and have a model interpret the video. This only works with certain Gemini models that
Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.7...v1.1.8
Audio File Upload on Playground: You can now upload audio files and have a model interpret the audio, do sentiment analysis, provide an audio transcri
Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.6...v1.1.7
Claude 3.7 Support: Added support for the latest Claude 3.7 Sonnet model
Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.5...v1.1.6
Audio Responses: Agents can now deliver audio responses (both with streaming and non-streaming).
The audio is in the agent.run_response.response_audio.
This only works with OpenAIChat with the gpt-4o-audio-preview model. See their docs for more on how it works. For example
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.utils.audio import write_audio_to_file
agent = Agent(
model=OpenAIChat(
id="gpt-4o-audio-preview",
modalities=["text", "audio"], # Both text and audio responses are provided.
audio={"voice": "alloy", "format": "wav"},
),
)
agent.print_response(
"Tell me a 5 second story"
)
if agent.run_response.response_audio is not None:
write_audio_to_file(
audio=agent.run_response.response_audio.base64_audio, filename=str(filename)
)
See the audio_conversation_agent cookbook to test it out on the Agent Playground.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.4...v1.1.5
Gmail Tools: Added get_emails_by_thread and send_email_reply methods to GmailTools.
get_emails_by_thread and send_email_reply methods to GmailTools.openai would be required for chunking even if a model was passed.Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.3...v1.1.4
Gemini Tool-Call History: Fixed an issue where Gemini rejected tool-calls from historic messages.
Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.2...v1.1.3
Reasoning with o3 Models: Reasoning support added for OpenAI’s o3 models.
Reasoning with o3 Models: Reasoning support added for OpenAI’s o3 models.
Gemini embedder update: Updated the GeminiEmbedder to use the new Google’s genai SDK. This update introduces a slight change in the interface:
# Before
embeddings = GeminiEmbedder("models/text-embedding-004").get_embedding(
"The quick brown fox jumps over the lazy dog."
)
# After
embeddings = GeminiEmbedder("text-embedding-004").get_embedding(
"The quick brown fox jumps over the lazy dog."
)
on_bad_vectors as parameters.Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.1...v1.1.2
…audio generation API calls. This is a breaking change, as the parameters for the ModelsLabTools class have changed. The url and fetch_url parameters h…
File / Image Uploads on Agent UI: Agent UI now supports file and image uploads with prompts.
.pdf .csv .txt .docx .json.png .jpeg .jpg .webpFirecrawl Custom API URL: Allowed users to set a custom API URL for Firecrawl.
Updated ModelsLabTools Toolkit Constructor: The constructor in /libs/agno/tools/models_labs.py has been updated to accommodate audio generation API calls. This is a breaking change, as the parameters for the ModelsLabTools class have changed. The url and fetch_url parameters have been removed, and API URLs are now decided based on the file_type provided by the user.
MODELS_LAB_URLS = {
"MP4": "https://modelslab.com/api/v6/video/text2video",
"MP3": "https://modelslab.com/api/v6/voice/music_gen",
"GIF": "https://modelslab.com/api/v6/video/text2video",
}
MODELS_LAB_FETCH_URLS = {
"MP4": "https://modelslab.com/api/v6/video/fetch",
"MP3": "https://modelslab.com/api/v6/voice/fetch",
"GIF": "https://modelslab.com/api/v6/video/fetch",
}
The FileType enum now includes MP3 type:
class FileType(str, Enum):
MP4 = "mp4"
GIF = "gif"
MP3 = "mp3"
MistralEmbedder.Full Changelog: https://github.com/agno-agi/agno/compare/v1.1.0...v1.1.1
Models Refactor: A complete overhaul of our models implementation to improve on performance and to have better feature parity across models.
AwsBedrock.Gemini . This will allow for easier integration of Gemini features in future.exponential_backoff is set to True. <docs>GoogleSearch to GoogleSearchTools for consistency.Gemini implementation directly on the Vertex API has been replaced by the Google SDK implementation of Gemini.Gemini implementation via the OpenAI client has been replaced by the Google SDK implementation of Gemini.OllamaHermes has been removed as the implementation of Ollama was improved.Full Changelog: https://github.com/agno-agi/agno/compare/v1.0.8...v1.1.0
Your coding agent can read these notes before it upgrades. Set up the MCP server →