|
2 | 2 | title: "Product updates" |
3 | 3 | mode: "wide" |
4 | 4 | --- |
| 5 | +<Update label="2025-04-23" description="v1.4.0"> |
| 6 | +# |
| 7 | + |
| 8 | +## New Features: |
| 9 | + |
| 10 | +- **Memory Generally Available**: We have made improvements and adjustments to how Agentic user memory management works. This is now out of beta and generally available. See these [examples](https://github.com/agno-agi/agno/tree/main/cookbook/agent_concepts/memory) and these [docs](https://docs.agno.com/agents/memory) for more info. |
| 11 | +- **OpenAI Tools**: Added `OpenAITools` to enable text-to-speech and image generation through OpenAI’s APIs. |
| 12 | +- **Zep Tools**: Added `ZepTools` and `AsyncZepTools` to manage memories for your Agent using `zep-cloud` |
| 13 | + |
| 14 | +## Improvements: |
| 15 | + |
| 16 | +- **Azure AI Foundry Reasoning**: Added support for reasoning models via Azure AI Foundry. E.g. Deepseek-R1. |
| 17 | +- **Include/Exclude Tools**: Added `include_tools` and `exclude_tools` for all toolkits. This allows for selective enabling / disabling of tools inside toolkits, which is especially useful for larger toolkits. |
| 18 | + |
| 19 | +## Bug Fixes: |
| 20 | + |
| 21 | +- **Gemini with Memory**: Fixed issue with `deepcopy` when Gemini is used with `Memory`. |
| 22 | + |
| 23 | +## Breaking Changes: |
| 24 | + |
| 25 | +- **Memory:** Agents will now by default use an improved `Memory` instead of the now deprecated `AgentMemory`. |
| 26 | + - `agent.memory.messages` → `run.messages for run in agent.memory.runs` (or `agent.get_messages_for_session()`) |
| 27 | + - `create_user_memories` → `enable_user_memories` and is now set on the Agent/Team directly. |
| 28 | + - `create_session_summary` → `enable_session_summaries` and is now set on the Agent/Team directly. |
| 29 | +</Update> |
| 30 | +<Update label="2025-04-21" description="v1.3.5"> |
| 31 | +## Improvements: |
| 32 | + |
| 33 | +- **Further Async Vector DB Support**: Support added for: |
| 34 | + - [Clickhouse](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/knowledge/vector_dbs/clickhouse_db/async_clickhouse.py) |
| 35 | + - [ChromaDB](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/knowledge/vector_dbs/chroma_db/async_chroma_db.py) |
| 36 | + - [Cassandra](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/knowledge/vector_dbs/cassandra_db/async_cassandra_db.py) |
| 37 | + - [PineconeDB](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/knowledge/vector_dbs/pinecone_db/async_pinecone_db.py) |
| 38 | + - [Pgvector](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/knowledge/vector_dbs/pgvector_db/async_pg_vector.py) |
| 39 | +- **Reasoning on Agno Platform**: |
| 40 | + - Added extensive support for reasoning on the Agno Platform. Go see your favourite reasoning agents in action! |
| 41 | + - Changes from SDK |
| 42 | + - send proper events in different types of reasoning and populate the `reasoning_content` on `RunResponse` for `stream/non-stream`, `async/non-async` |
| 43 | + - unified json structure for all types of reasoning in `Reasoning events` |
| 44 | +- **Google Caching Support**: Added support for caching files and sending the cached content to Gemini. |
| 45 | + |
| 46 | +## Bug Fixes |
| 47 | + |
| 48 | +- **Firecrawl Scrape**: Fixed issues with non-serializable types for during Firecrawl execution. https://github.com/agno-agi/agno/issues/2883 |
| 49 | +</Update> |
| 50 | +<Update label="2025-04-18" description="v1.3.4"> |
| 51 | +## New Features: |
| 52 | + |
| 53 | +- **Web Browser Tool:** Introduced a `webbrowser` tool for agents to interact with the web. |
| 54 | +- **Proxy Support:** Added `proxy` parameter support to both URL and PDF tools for network customization. |
| 55 | + |
| 56 | +## Improvements: |
| 57 | + |
| 58 | +- **Session State:** Added examples for managing session state in agents. |
| 59 | +- **AzureOpenAIEmbedder:** Now considers `client_params` passed in the `client_params` argument for more flexible configuration. |
| 60 | +- **LiteLLM:** Now uses built-in environment validation to simplify setup. |
| 61 | +- **Team Class:** Added a `mode` attribute to team data serialization for enhanced team configuration. |
| 62 | +- **Insert/Upsert/Log Optimization:** insert/upsert/log_info operations now trigger only when documents are present in the reader. |
| 63 | +- **Database Preference:** Session state now prefers database-backed storage if available. |
| 64 | +- **Memory Management:** Internal memory system updated for better session handling and resource efficiency. |
| 65 | +- **Module Exports:** Init files that only import now explicitly export symbols using `__all__`. |
| 66 | + |
| 67 | +## Bug Fixes: |
| 68 | + |
| 69 | +- **DynamoDB Storage:** Fixed an issue with storage handling in DynamoDB-based setups. |
| 70 | +- **DeepSeek:** Fixed a bug with API key validation logic. |
| 71 | +</Update> |
| 72 | +<Update label="2025-04-17" description="v1.3.3"> |
| 73 | +## Improvements: |
| 74 | + |
| 75 | +- **Gemini File Upload**: Enabled direct use of uploaded files with Gemini. |
| 76 | +- **Metrics Update**: Added audio, reasoning and cached token counts to metrics where available on models. |
| 77 | +- **Reasoning Updates**: We now natively support Ollama and AzureOpenAI reasoning models. |
| 78 | + |
| 79 | +## Bug Fixes: |
| 80 | + |
| 81 | +- **PPrint Util Async**: Added `apprint_run_response` to support async. |
| 82 | +- **Mistral Reasoning:** Fixed issues with using a Mistral model for chain-of-thought reasoning. |
| 83 | +</Update> |
5 | 84 |
|
6 | 85 | <Update label="2025-04-16" description="v1.3.2"> |
7 | 86 | ## New Features: |
|
0 commit comments