90c30fa62b
Bump litellm to 1.60.2 ( fixes #34 ) ( #488 )
2025-02-05 11:43:02 +01:00
26c733c745
Fix undefined `step_number` in single_step run ( #495 )
...
* Fix undefined step_number
* Test step_number is defined after single_step run
---------
Co-authored-by: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
2025-02-05 09:00:19 +01:00
8b1dd44010
Fix link in README.md ( #496 )
...
Helium link was pointing to wrong repo
2025-02-05 08:25:56 +01:00
8b02821ac2
Open Deep Research ( #317 )
...
* Create an open Deep Research
Co-authored-by: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
---------
Co-authored-by: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
2025-02-04 17:13:21 +01:00
a8918f7a60
fix tool push to hub ( #460 )
2025-02-04 12:35:04 +01:00
a6d2cdaaef
Added HfApiModel import to web browser example ( #461 )
2025-02-04 12:34:15 +01:00
d69ae028fa
Simplify managed agents ( #484 )
...
* Simplify managed agents
2025-02-03 21:19:54 +01:00
dd84e7333d
Fixed demo typo in README.md ( #481 )
2025-02-03 17:16:56 +01:00
6d72ea7283
fix ollama integration by forcing flat messages ( #406 )
2025-02-03 16:54:56 +01:00
183869de04
Fix SpeechToTextTool new instance ( #478 )
...
* Test SpeechToTextTool new instance
* Fix SpeechToTextTool new method
2025-02-03 11:42:03 +01:00
44f94eaa2d
Improve Readme: shorter intro, VLMs, MCP, etc ( #459 )
...
* Improve Readme: shorter intro, VLMs, MCP, etc
2025-02-03 11:13:49 +01:00
318b9e6700
Remove default max_tokens for all models ( #475 )
2025-02-03 11:10:20 +01:00
42f95d8ee1
Add visualization method to display the agent' structure as a tree 🌳 ( #470 )
2025-02-03 11:07:05 +01:00
39908439d2
Fix link to Helium repository in README.md ( #471 )
2025-02-03 08:00:44 +01:00
93c433c81f
Add ToC and CLI docs ( #455 )
...
---------
Co-authored-by: Aymeric Roucher <69208727+aymeric-roucher@users.noreply.github.com>
2025-01-31 16:26:42 +01:00
e26aed68e8
Bump dev version: v1.8.0.dev0 ( #451 )
2025-01-31 14:21:02 +01:00
1adf5df031
fix minor issue in e2b ( #436 )
2025-01-31 13:53:59 +01:00
b453d63f33
Add web browser example to doc ( #439 )
2025-01-31 13:47:45 +01:00
cedf63cde7
Test get_clean_message_list ( #448 )
...
* Test get_clean_message_list
* Test get_clean_message_list
2025-01-31 13:47:02 +01:00
b228ffa328
docs ( #447 )
2025-01-31 13:40:16 +01:00
f1a9b83443
Improve code execution logs in case of error by showing print outputs ( #446 )
...
* Improve code execution logs in case of error by still showing print outputs
* Improve action step testing
* Number steps starting at 1
2025-01-31 12:34:32 +01:00
5f2147a17d
Remove unused raw arg ( #445 )
2025-01-31 12:00:10 +01:00
ebae61f5ba
Remove duplicated final_memory_step creation ( #444 )
2025-01-31 11:59:53 +01:00
10407813e8
Fix get safe module ( #405 )
...
* expose get_safe_module lazy loading issue
* fix get_safe_module lazy imports
* add six as explicit tests dependency
* log dangerous attributes
* refactor get_safe_module test
2025-01-31 08:25:22 +01:00
181a500c5d
Fix and test MemoryStep ( #432 )
...
* Test MemoryStep
* Remove unused MemoryStep.raw attribute
2025-01-30 21:24:39 +01:00
42d97716fe
Fix MultiStepAgent.planning_step message content ( #437 )
...
* Fix MultiStepAgent.planning_step message content
2025-01-30 21:18:30 +01:00
6d0e4e49fc
Update benchmark with Hub datasets ( #412 )
...
* Use smolagents-benchmark Hub datasets
* Push results to Hub
* Fix style
* Add Constants section at the top
* Set DATE as constant
2025-01-30 19:21:32 +01:00
aa55f137e5
Remove explicit model arg in HfApiModel - which wouldn't run without Pro ( #373 )
...
* Remove explicit model arg in HfApiModel - which wouldn't run without Pro
2025-01-30 18:55:09 +01:00
023419bf92
Add web search tool and make prompt positional arg ( #435 )
2025-01-30 18:13:08 +01:00
25c5b50222
Fix import from deleted logger ( #433 )
2025-01-30 17:34:05 +01:00
fa1f8d0154
Add CLI for smolagents ( #431 )
...
---------
Co-authored-by: Merve Noyan <merveenoyan@gmail.com>
2025-01-30 15:56:50 +01:00
595781b82d
Test memory ( #428 )
...
* Test memory
* Add memory tests to CI
2025-01-30 13:51:18 +01:00
37f549f4aa
Fix installation instruction for GradioUI in error message ( #418 )
2025-01-30 13:25:53 +01:00
20383f0914
Fix regressions, refactor logging and improve replay function ( #419 )
...
* Refactor logging and improve replay function
* Fix test
* Remode unnecessary dict method
* Remove logger import
---------
Co-authored-by: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
2025-01-30 11:32:28 +01:00
c0abd2134e
Fix `vlm_web_browser.py` example ( #410 )
...
* Update `vlm_web_browser.py` example
Fixed a typo which meant that the images were never being remove for lean processing
---------
Co-authored-by: Aymeric <aymeric.roucher@gmail.com>
2025-01-30 02:17:00 +01:00
dcbbe448af
Make web browser example a CLI script ( #416 )
...
* Makes web browser example a CLI script
---------
Co-authored-by: Merve Noyan <mervenoyan@Merve-MacBook-Pro.local>
Co-authored-by: Aymeric <aymeric.roucher@gmail.com>
2025-01-30 01:55:54 +01:00
3b8e519f77
minor example fix ( #423 )
2025-01-30 01:04:30 +01:00
d3912c70cf
Support third-party Inference providers in `HfApiModel` ( #422 )
...
* Add `provider` param to `HfApiModel `, update guided_tour.md
---------
Co-authored-by: Aymeric <aymeric.roucher@gmail.com>
2025-01-30 01:03:09 +01:00
b1742ed06c
Update pyproject.toml ( #408 )
2025-01-29 18:39:11 +01:00
c6eb9526f1
Untangling Logging ( #316 )
...
* Deep refacto that disentangled logging logic between logging (informing the user via console outputs) and memory (storing what happened in the agent).
---------
Co-authored-by: benediktstroebl <50178209+benediktstroebl@users.noreply.github.com>
Co-authored-by: Aymeric <aymeric.roucher@gmail.com>
2025-01-29 16:27:04 +01:00
882b134f35
Fix return type of generator function in `Agent._run()` ( #409 )
...
* Fix return type of generator function in `Agent._run()`
2025-01-29 15:35:32 +01:00
022947a2a5
Bump dev version: v1.7.0.dev0 ( #390 )
2025-01-28 12:06:07 +01:00
7a2f300b2a
Add test for DDGS Tool kwargs ( #387 )
2025-01-28 11:02:21 +01:00
ad5f84b101
Fix blocking of os in authorized imports ( #386 )
2025-01-28 11:00:43 +01:00
a4f89b68b2
Add tool saving test ( #389 )
...
* Add tool saving test
* Format
2025-01-28 10:58:53 +01:00
cc21135188
Test import without extras ( #370 )
...
* Test import without extras
* Add import test to CI
* Use uv run
2025-01-28 10:57:14 +01:00
242a6e59c5
Docs: Text to sql example - minor naming / dedupe ( #376 )
...
* Fix up minor naming oddities
Dedupe insert row logic
* Improve readability
2025-01-28 10:43:06 +01:00
33b38e6cb7
fix final_answer issue in e2b_executor ( #319 )
2025-01-28 10:41:32 +01:00
2105811da6
DuckDuckGoSearchTool: add ddgs_kwargs parameter to constructor ( #372 )
...
* DuckDuckGoSearchTool: add ddgs_kwargs parameter to constructor for flexible configuration
2025-01-28 10:11:33 +01:00
8178eeca65
Additional parameters for openai ( #385 )
2025-01-28 10:01:12 +01:00
Taha Yassine
vanrohan
Aymeric Roucher
Parteek
Sergio Paniego Blanco
hante
Alex
Albert Villanova del Moral
Drew Ross
Merve Noyan
August Moharrami
Antoine Jeannot
Sanjeed
Jan
Abubakar Abid
RolandJAAI
Julien Chaumond
Clémentine Fourrier
Graham
onukura
Touseef Ahmad