| .. |
|
async_agent
|
Change default InferenceClient model to Qwen/Qwen3-Next-80B-A3B-Thinking (#1813)
|
2025-10-16 11:55:31 +02:00 |
|
open_deep_research
|
Fix run_gaia.py token_counts when managed agent is called more than once (#1878)
|
2025-12-17 13:48:00 +01:00 |
|
plan_customization
|
Fix code formatting in plan customization README (#2680)
|
2026-08-22 14:00:16 +02:00 |
|
server
|
Change default InferenceClient model to Qwen/Qwen3-Next-80B-A3B-Thinking (#1813)
|
2025-10-16 11:55:31 +02:00 |
|
smolagents_benchmark
|
Fix minor benchmark script bugs (#1822)
|
2025-10-18 23:13:12 +02:00 |
|
agent_from_any_llm.py
|
Remove 'Server' from model names in doc (#1812)
|
2025-10-16 15:10:09 +02:00 |
|
gradio_ui.py
|
Transfer aggregation of streaming events off the Model class (#1449)
|
2025-06-20 11:45:00 +02:00 |
|
inspect_multiagent_run.py
|
Fix typo cleanups across docs, examples, and tests (#2208)
|
2026-05-14 14:42:18 +02:00 |
|
multi_llm_agent.py
|
remove plural from named argument return_full_results in examples (#1434)
|
2025-06-17 10:21:31 +02:00 |
|
multiple_tools.py
|
Proposition: retry on rate limit errors (#1801)
|
2025-10-15 19:09:38 +02:00 |
|
rag.py
|
Change default InferenceClient model to Qwen/Qwen3-Next-80B-A3B-Thinking (#1813)
|
2025-10-16 11:55:31 +02:00 |
|
rag_using_chromadb.py
|
Change default InferenceClient model to Qwen/Qwen3-Next-80B-A3B-Thinking (#1813)
|
2025-10-16 11:55:31 +02:00 |
|
sandboxed_execution.py
|
Remove remote WasmExecutor (#2321)
|
2026-05-29 07:03:46 +02:00 |
|
structured_output_tool.py
|
Support MCP structured output and output schema (#1663)
|
2025-08-22 11:49:16 +02:00 |
|
text_to_sql.py
|
rename HfApiModel to InferenceClientModel (#1198)
|
2025-04-16 15:42:11 +02:00 |
