cfbd527438
Add cool GIF of agent run inspection using Phoenix ( #277 )
...
* Add cool GIF of agent run inspection using Phoenix
2025-01-21 13:43:48 +01:00
16f7910df8
Make e2b optional dependency ( #292 )
...
* Make e2b optional dependency with extra
* Make e2b imports optional
* Update e2b docs
2025-01-21 12:17:24 +01:00
257c1fe33b
Update guided_tour.md ( #287 )
2025-01-21 11:18:45 +01:00
1e745c7a34
Update building_good_agents.md ( #283 )
2025-01-21 11:03:51 +01:00
fb23e91a21
Add huggingface-hub as required dependency ( #288 )
2025-01-21 10:50:08 +01:00
0e0d73b096
Try first dunder method in evaluate_augassign ( #285 )
...
* Test evaluate_augassign
2025-01-21 10:41:25 +01:00
a2b37caff1
Fix CI quality ( #286 )
2025-01-21 10:40:15 +01:00
bd08d6485d
Added Hindi docs for smolagents ( #279 )
2025-01-20 19:30:31 +01:00
a4612c98dc
Fix (interpreter security): builtins functions passed as tools enable the use of compile, eval, exec ( #274 )
2025-01-20 17:06:47 +01:00
7a91123729
Improve python executor's error logging ( #275 )
...
* Improve python executor's error logging
2025-01-20 15:57:16 +01:00
3c18d4d588
Python interpreter: improve suggestions for possible mappings ( #266 )
2025-01-20 11:40:43 +01:00
d19ebc7a48
Make import time faster (optional deps + delay imports) ( #253 )
...
* adapt docs
* optional in pyproject.toml
* get rid of some transformers imports
* optional transformers in models.py
* gradio, transformers, litellm
* small refacto AgentType
* merge conflicts
* mouaif
* fix tests
* AgentText no longer a str
* Add back AgentType as str/Image
* fixed for good
2025-01-20 10:59:43 +01:00
a2ca95107f
Bump version to 1.5.0.dev ( #256 )
...
* Bump version to 1.5.0.dev
* Fix style
---------
Co-authored-by: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
2025-01-20 10:59:16 +01:00
35f719164b
Fix Bug in from_langchain in tools.py ( #268 )
...
* Fix from_langchain in tools.py
2025-01-20 10:50:03 +01:00
3178b18aab
Remove unused and undocumented parameter ( #273 )
2025-01-20 10:45:55 +01:00
0abd91cf72
Improve tool call argument parsing ( #267 )
...
* Improve tool call argument parsing
2025-01-20 10:44:40 +01:00
89a6350fe2
Fix quality ( #272 )
2025-01-20 09:49:20 +01:00
06a8c546b9
fix additional_args and num_ctx examples also in zh docs ( #260 )
2025-01-18 19:09:50 +01:00
6e1373a324
Add linter rules + apply make style ( #255 )
...
* Add linter rules + apply make style
2025-01-18 19:01:15 +01:00
5aa0f2b53d
Fixes bug no attribute 'logger' ( #259 )
2025-01-18 18:31:19 +01:00
34810986e0
refactor: update model type to ChatMessage in agent classes ( #263 )
2025-01-18 18:27:48 +01:00
e3ae1800e2
Fixes before release ( #254 )
...
* Fixes before release
2025-01-17 20:20:28 +01:00
a4d029da88
add support for MCP Servers tools as `ToolCollection` ( #232 )
...
* add support for tool collection from mcp servers
* add forgotten documentation
* fix link missing in documentation
* fix linting in CI, bumpruff to use modern version
* mcpadapt added as optional dependencies
* use classmethod for from_hub and from_mcp to better reflect the fact that they return a ToolCollection
* Update src/smolagents/tools.py
Co-authored-by: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
* Update src/smolagents/tools.py
Co-authored-by: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
* Test ToolCollection.from_mcp
* Rename to mcp extra
* Add mcp extra to test extra
* add a test for from_mcp
* fix typo
* fix tests
* Test ToolCollection.from_mcp
(cherry picked from commit 9284d9ea8cf24d3c934e35a38dfe34f3ce31cef3)
* Make all pytest tests
---------
Co-authored-by: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
2025-01-17 19:41:43 +01:00
7d6599e430
docs: small fixes in docs ( #245 )
2025-01-17 19:20:25 +01:00
d1b8a78783
Max length of "print" outputs as a parameter of an agent ( #209 )
...
* Print outputs max length as a parameter
2025-01-17 19:16:47 +01:00
116b12e93a
chore: unset console width, utilize auto detect feature ( #196 )
2025-01-17 19:15:53 +01:00
3e1c979dac
Add Chinese translations for multi-agent example ( #246 )
...
* Add first complete Chinese translation
2025-01-17 19:12:59 +01:00
e30ec8ac91
Set ollama context lenght in example to 8192 to make it work ( #252 )
...
* set ollama context length in example
2025-01-17 18:41:34 +01:00
58b18f5655
Remove dependency on _is_package_available from transformers ( #247 )
2025-01-17 18:38:33 +01:00
6db75183ff
Fix style
2025-01-17 18:04:16 +01:00
d8591dc703
Improve OpenAIServerModel by making api_base and api_url optional (will then point to OpenAI server)
2025-01-17 18:03:51 +01:00
68933e7e90
Make openai dependency optional ( #236 )
...
* Make openai optional dependency
* Set openai as an extra dependency
2025-01-17 16:46:18 +01:00
1f8fd72acb
Clean makefile, pyproject.toml and CI ( #229 )
...
* Clean makefile / pyproject.toml / .github
* new tests after
* add back sqlalchemy
* disable docs tests in CI
* continue on error
* correct continue on error
* Remove all_docs test
2025-01-17 13:18:06 +01:00
fabc59aa08
Fix missing python modules in CodeAgent system prompt ( #226 )
...
* fix modules in system prompt + test
2025-01-17 11:59:30 +01:00
11a738e53a
Add trust_remote_code arg to TransformersModel ( #240 )
2025-01-17 11:55:36 +01:00
c255c1ff84
Fix subpackage import vulnerability ( #238 )
...
* Fix subpackage import vulnerability
2025-01-17 11:40:49 +01:00
d5c2ef48e7
Add resizeable option to Gradio UI component for better usabilty ( #234 )
2025-01-16 23:05:23 +01:00
c56d73731d
Dead Link to Duck Duck Go search tool ( #233 )
...
* Update multiagents.md URL to DuckDuckGo
2025-01-16 23:04:40 +01:00
b4091cb5ce
Allow passing kwargs to all models ( #222 )
...
* Allow passing kwargs to all models
2025-01-16 23:03:38 +01:00
a1d8f3c398
fix tool example with additional args ( #228 )
2025-01-16 23:00:11 +01:00
a4ec1e5be3
Return textboxes on file upload errors ( #214 )
2025-01-16 16:33:01 +01:00
fdf4fe49ba
Fix additional args in stream_to_gradio ( #221 )
2025-01-16 15:47:23 +01:00
2a69f1574e
Fix vanilla model answer in example benchmark ( #219 )
2025-01-16 12:04:41 +01:00
72b01a9909
Restore previous agents.py
2025-01-16 11:54:23 +01:00
96ebe01dc7
Add license_to_call graphic to documentation index
2025-01-16 11:48:16 +01:00
34a718cf02
Fix mascot positioning
2025-01-16 11:40:23 +01:00
40087aad0b
Update mascot
2025-01-16 11:38:09 +01:00
2ae590edf4
Rename the benchmark dataset split from train to test ( #216 )
2025-01-16 09:57:00 +01:00
4449c51cad
Align data types in example benchmark ( #205 )
2025-01-16 09:54:47 +01:00
98c6688c3d
Add pip install for instrumentation
2025-01-16 09:39:28 +01:00
Aymeric Roucher
Albert Villanova del Moral
Sanjeed
Derek Alia
Parteek
tandiapa
Lucain
RolandJAAI
joaopauloschuler
Jan
Guillaume Raille
Moritz Laurer
Ilya Gusev
Lê Thông
Fanwang Meng
Aymeric
Edward Beeching
matterattetatte
stackviolator