mirror of
https://github.com/agno-agi/agno.git
synced 2026-10-12 02:10:54 +00:00
Sannya Singal
ccdd11eafd
## Summary Follow-up to #10115. A reranker can be configured in two places, which leaves users guessing which one applies. This deprecates the vector db one and moves to use the reranker on Knowledge. `Knowledge` is the better home for it: it applies to every vector db rather than the 13 that implement the parameter, it can widen the candidate pool for rerankers that need one, and it supports async. Setting a reranker on a vector db now logs: Setting a reranker on the vector db is deprecated. Pass it to Knowledge instead, which applies it to every vector db and can widen the candidate pool for rerankers that need one: Knowledge(vector_db=..., reranker=...). Nothing is disabled today. A reranker set on a vector db still runs exactly as before, the only change is the log line. The one behavioural difference, Knowledge winning when both are set which was landed in #10115, not here. The warning lives on the `reranker` setter on the `VectorDb` base, which every adapter's assignment already routes through. Also updated: the "configured in both places" warning now names the deprecation and says which one to keep, and nine adapter docstrings carry a deprecation note and cookbooks are migrated as well. ## Type of change - [ ] Bug fix - [ ] New feature - [ ] Breaking change - [ ] Improvement - [ ] Model update - [ ] Other: --- ## Checklist - [ ] Code complies with style guidelines - [ ] Ran format/validation scripts (`./scripts/format.sh` and `./scripts/validate.sh`) - [ ] Self-review completed - [ ] Documentation updated (comments, docstrings) - [ ] Examples and guides: Relevant cookbook examples have been included or updated (if applicable) - [ ] Tested in clean environment - [ ] Tests added/updated (if applicable) ### Duplicate and AI-Generated PR Check - [ ] I have searched existing [open pull requests](https://github.com/agno-agi/agno/pulls) and confirmed that no other PR already addresses this issue - [ ] If a similar PR exists, I have explained below why this PR is a better approach - [ ] Check if this PR was entirely AI-generated (by Copilot, Claude Code, Cursor, etc.) --- ## Additional Notes Add any important context (deployment instructions, screenshots, security considerations, etc.)
Agent Teams
Cookbooks for building multi-agent teams in Agno.
Prerequisites
- Load environment variables with
direnv allow(for exampleOPENAI_API_KEY). - Use
.venvs/demo/bin/pythonto run examples. - Some examples require external services (for example PostgreSQL, LanceDB, Infinity server, or AgentOS remote instances).
Directories
01_quickstart/- Core team coordination patterns, including route/broadcast/tasks and nested teams.02_modes/- Team execution modes (coordinate, route, broadcast, tasks) with examples for each.03_tools/- Custom tools and tool hook patterns.04_structured_input_output/- Structured input/output schemas, overrides, and streaming.05_knowledge/- Team knowledge, filters, and custom retrievers.06_memory/- Memory manager, agentic memory, and LearningMachine examples.07_session/- Session persistence, options, summaries, and history search.08_streaming/- Response streaming and event monitoring.09_context_management/- Context filtering, introductions, and few-shot context.10_context_compression/- Tool-result compression and compression manager usage.11_reasoning/- Multi-purpose reasoning team patterns.12_learning/- Team learning patterns (always, configured, entity memory, session planning, learned knowledge, decision log).13_hooks/- Input pre-hooks, output post-hooks, and stream hooks.14_run_control/- Cancellation, retries, model inheritance, remote teams, and background execution.15_distributed_rag/- Multi-member distributed retrieval with PgVector/LanceDB/reranking.16_search_coordination/- Coordinated RAG/search patterns across members.17_dependencies/- Runtime dependencies in context, tools, and member flows.18_guardrails/- Prompt-injection, moderation, and PII protections.19_multimodal/- Audio, image, and video workflows.20_human_in_the_loop/- Confirmation, external execution, and user-input-required flows.21_state/- Shared session state across members and nested teams.22_metrics/- Team/session/member metrics inspection.23_checkpointing/- Checkpointing and crash recovery for team runs.23_remote_agents/- Remote agents as team members.24_regenerate/- Redo the last response of a team run.25_time_travel/- Rewind a team run and resume from an earlier point.26_fork_session/- Fork a whole team session into a new one.27_result_offloading/- Member answers and large tool results stored as files, envelopes in the leader's transcript.