v1.5.0

Changelog

New Features:

• Azure OpenAI Tools: Added image generation via Dall-E via Azure AI Foundry.
• OpenTelemetry Instrumentation: We have contributed to the OpenInference project and added an auto-instrumentor for Agno agents. This adds tracing instrumentation for Agno Agents for any OpenTelemetry-compatible observability provider. These include Arize, Langfuse and Langsmith. Examples added to illustrate how to use each one (here).
• Evals Updates: Added logic to run accuracy evaluations with pre-generated answers and minor improvements for all evals classes.
• Hybrid Search and Reranker for Milvus Vector DB: Added support for hybrid_search on Milvus.
• MCP with Streamable-HTTP: Now supporting the streamable-HTTP transport for MCP servers.

Improvements:

• Knowledge Filters Cookbook: Instead of storing the sample data locally, we now pull it from s3 at runtime to keep the forking of the repo as light as possible.

Bug Fixes:

• Team Model State: Fixed issues related to state being shared between models on teams.
• Concurrent Agent Runs: Fixed certain race-conditions related to running agents concurrently.

Breaking changes:

• Evals Refactoring:
  • Our performance evaluation class has been renamed from PerfEval to PerformanceEval
  • Our accuracy evaluation class has new required fields: agent, prompt and expected_answer
• Concurrent Agent Runs: We removed duplicate information from some events during streaming (stream=True). Individual events will have more relevant data now.

What's Changed

• cookbook/playground: use ag setup to authenticate by @continuous1024 in #2996
• Modify toolkit to support new image generation model by @Mustafa-Esoofally in #3147
• Image generation App by @Mustafa-Esoofally in #3146
• Create an Azure OpenAI tool with image generation by @ArvidB3 in #2536
• ci: Add PR linting workflow and update contributing guidelines by @aryan-dani in #3032
• [feat] Replace markdown issue templates with YAML forms by @aryan-dani in #3034
• [fix] Make models stateless by @dirkbrnd in #3140
• memory-v2-dict-fix-ag-3058 by @ysolanky in #3133
• chore: pull filter data from s3 at runtime by @kausmeows in #3174
• feat: Supabase MCP app by @Mustafa-Esoofally in #3175
• chore: refactor accuracy eval logic by @manuhortet in #2916
• feat: Arize Phoenix via OpenInference by @dirkbrnd in #3136
• fix: concurrent-arun-calls-mixing-responses by @kausmeows in #3138
• feat: add hybrid search support in milvus vdb by @kausmeows in #3164
• feat: Add support for streamable-http in MCPTools by @kkpalczewski in #3159
• feat: implement cli auth get by @pritipsingh in #3049
• chore: Release 1.5.0 by @dirkbrnd in #3171

New Contributors

• @continuous1024 made their first contribution in #2996
• @ArvidB3 made their first contribution in #2536
• @aryan-dani made their first contribution in #3032
• @kkpalczewski made their first contribution in #3159

Full Changelog: v1.4.6...v1.5.0