update from hf

.github/workflows/quality.yml

@@ -3,21 +3,33 @@ name: Quality Check
 on: [pull_request]
 
 jobs:
-  quality:
+  check_code_quality:
     runs-on: ubuntu-latest
+    env:
+      UV_HTTP_TIMEOUT: 600 # max 10min to install deps
+
     steps:
-    - uses: actions/[email protected]
-    - name: Set up Python 3.9
-      uses: actions/setup-python@v3
-      with:
-        python-version: 3.10
-        cache: 'pip'
-        cache-dependency-path: 'setup.py'
-    - name: Install Python dependencies
-      run: pip install -e .[quality]
-    - name: Run Quality check
-      run: make quality
-    - name: Check if failure
-      if: ${{ failure() }}
-      run: |
-        echo "Quality check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and rerun 'make style; make quality;'" >> $GITHUB_STEP_SUMMARY
+      - uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.10"
+
+      # Setup venv
+      # TODO: revisit when https://github.com/astral-sh/uv/issues/1526 is addressed.
+      - name: Setup venv + uv
+        run: |
+          pip install --upgrade uv
+          uv venv
+
+      - name: Install dependencies
+        run: uv pip install "smolagents[test] @ ."
+      - run: uv run ruff check tests src # linter
+      - run: uv run ruff format --check tests src # formatter
+
+      # Run type checking at least on smolagents root file to check all modules
+      # that can be lazy-loaded actually exist.
+      # - run: uv run mypy src/smolagents/__init__.py --follow-imports=silent --show-traceback
+
+      # Run mypy on full package
+      # - run: uv run mypy src

.github/workflows/tests.yml

@@ -0,0 +1,59 @@
+name: Python tests
+
+on: [pull_request]
+
+jobs:
+  build-ubuntu:
+    runs-on: ubuntu-latest
+    env:
+      UV_HTTP_TIMEOUT: 600 # max 10min to install deps
+
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+
+
+      # Setup venv
+      # TODO: revisit when https://github.com/astral-sh/uv/issues/1526 is addressed.
+      - name: Setup venv + uv
+        run: |
+          pip install --upgrade uv
+          uv venv
+
+      # Install dependencies
+      - name: Install dependencies
+        run: |
+          uv pip install "smolagents[test] @ ."
+
+      - name: Agent tests
+        run: |
+          uv run pytest -sv ./tests/test_agents.py
+      - name: Final answer tests
+        run: |
+          uv run pytest -sv ./tests/test_final_answer.py
+      - name: Models tests
+        run: |
+          uv run pytest -sv ./tests/test_models.py
+      - name: Monitoring tests
+        run: |
+          uv run pytest -sv ./tests/test_monitoring.py
+      - name: Python interpreter tests
+        run: |
+          uv run pytest -sv ./tests/test_python_interpreter.py
+      - name: Search tests
+        run: |
+          uv run pytest -sv ./tests/test_search.py
+      - name: Tools tests
+        run: |
+          uv run pytest -sv ./tests/test_tools.py
+      - name: Types tests
+        run: |
+          uv run pytest -sv ./tests/test_types.py

.github/workflows/trufflehog.yml

@@ -0,0 +1,18 @@
+on:
+  push:
+
+name: Secret Leaks
+
+permissions:
+  contents: read
+
+jobs:
+  trufflehog:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Secret Scanning
+        uses: trufflesecurity/trufflehog@main

README.md

@@ -38,6 +38,9 @@ limitations under the License.
 
 🌐 **Support for any LLM**: it supports models hosted on the Hub loaded in their `transformers` version or through our inference API, but also supports models from OpenAI, Anthropic and many others via our [LiteLLM](https://www.litellm.ai/) integration.
 
+> [!NOTE]  
+> Check the our [launch blog post](https://huggingface.co/blog/smolagents) to learn more about `smolagents`!
+
 ## Quick demo
 
 First install the package.

docs/source/en/examples/multiagents.md

@@ -120,7 +120,7 @@ Now that we have all the tools `search` and `visit_webpage`, we can use them to
 
 Which configuration to choose for this agent?
 - Web browsing is a single-timeline task that does not require parallel tool calls, so JSON tool calling works well for that. We thus choose a `JsonAgent`.
-- Also, since sometimes web search requires exploring many pages before finding the correct answer, we prefer to increase the number of `max_iterations` to 10.
+- Also, since sometimes web search requires exploring many pages before finding the correct answer, we prefer to increase the number of `max_steps` to 10.
 
 ```py
 from smolagents import (
@@ -137,7 +137,7 @@ model = HfApiModel(model_id)
 web_agent = ToolCallingAgent(
     tools=[DuckDuckGoSearchTool(), visit_webpage],
     model=model,
-    max_iterations=10,
+    max_steps=10,
 )
 ```
 
@@ -169,7 +169,7 @@ manager_agent = CodeAgent(
 That's all! Now let's run our system! We select a question that requires both some calculation and research:
 
 ```py
-answer = manager_agent.run("If LLM trainings continue to scale up at the current rythm until 2030, what would be the electric power in GW required to power the biggest training runs by 2030? What does that correspond to, compared to some contries? Please provide a source for any number used.")
+answer = manager_agent.run("If LLM trainings continue to scale up at the current rhythm until 2030, what would be the electric power in GW required to power the biggest training runs by 2030? What does that correspond to, compared to some contries? Please provide a source for any number used.")
 ```
 
 We get this report as the answer:

docs/source/en/examples/rag.md

@@ -35,7 +35,7 @@ Let's build this system. 🛠️
 
 Run the line below to install required dependencies:
 ```bash
-!pip install smolagents pandas langchain langchain-community sentence-transformers faiss-cpu --upgrade -q
+!pip install smolagents pandas langchain langchain-community sentence-transformers rank_bm25 --upgrade -q
 ```
 To call the HF Inference API, you will need a valid token as your environment variable `HF_TOKEN`.
 We use python-dotenv to load it.
@@ -137,7 +137,7 @@ _Note:_ The Inference API hosts models based on various criteria, and deployed m
 from smolagents import HfApiModel, CodeAgent
 
 agent = CodeAgent(
-    tools=[retriever_tool], model=HfApiModel("meta-llama/Llama-3.3-70B-Instruct"), max_iterations=4, verbose=True
+    tools=[retriever_tool], model=HfApiModel("meta-llama/Llama-3.3-70B-Instruct"), max_steps=4, verbose=True
 )
 ```
 

docs/source/en/examples/text_to_sql.md

@@ -122,7 +122,7 @@ def sql_engine(query: str) -> str:
 
 Now let us create an agent that leverages this tool.
 
-We use the `CodeAgent`, which is transformers.agents’ main agent class: an agent that writes actions in code and can iterate on previous output according to the ReAct framework.
+We use the `CodeAgent`, which is smolagents’ main agent class: an agent that writes actions in code and can iterate on previous output according to the ReAct framework.
 
 The model is the LLM that powers the agent system. HfApiModel allows you to call LLMs using HF’s Inference API, either via Serverless or Dedicated endpoint, but you could also use any proprietary API.