Merge branch 'main' into struct-op-tools

.github/scripts/check_python_code_snippets.py

@@ -0,0 +1,86 @@
+import os
+import re
+from pathlib import Path
+import black
+
+DEFAULT_LINE_LENGTH = 70
+BASE_DIR = Path(__file__).resolve().parent
+MDX_DIR = BASE_DIR / "../../fern/pages"
+FILE_PATTERN = re.compile(r"\.mdx$")
+
+
+def find_files_by_pattern(directory, pattern):
+    """
+    Finds all files in the given directory that match the provided regex pattern.
+    """
+    directory = Path(directory).resolve()
+    if not directory.is_dir():
+        raise ValueError(f"Provided directory {directory} is not valid.")
+    return [f for f in directory.rglob('*') if f.is_file() and pattern.search(f.name)]
+
+
+def format_python_snippets_in_mdx(file_path, line_length=DEFAULT_LINE_LENGTH):
+    """
+    Formats Python code snippets inside MDX files using Black.
+    """
+    black_mode = black.FileMode(line_length=line_length)
+    code_block_pattern = re.compile(r"```python\n(.*?)\n```", re.DOTALL)
+
+    with open(file_path, 'r', encoding='utf-8') as file:
+        original_content = file.read()
+
+    def format_with_black(match):
+        code = match.group(1)
+        formatted_code = black.format_str(code, mode=black_mode)
+        return f"```python\n{formatted_code.strip()}\n```"
+
+    new_content = code_block_pattern.sub(format_with_black, original_content)
+
+    with open(file_path, 'w', encoding='utf-8') as file:
+        file.write(new_content)
+
+    return original_content, new_content
+
+
+def process_mdx_files(directory, file_pattern, line_length=DEFAULT_LINE_LENGTH, check_changes=False):
+    """
+    Processes all MDX files in the directory, formatting Python code snippets.
+
+    Args:
+        directory (Path or str): Path to the directory containing MDX files.
+        file_pattern (re.Pattern): Regex pattern to match MDX files.
+        line_length (int): Line length to use for Black formatting.
+        check_changes (bool): If True, raises an exception if changes are detected.
+    """
+    matching_files = find_files_by_pattern(directory, file_pattern)
+    files_changed = []
+
+    for file_path in matching_files:
+        original_content, new_content = format_python_snippets_in_mdx(file_path, line_length)
+
+        if original_content != new_content:
+            files_changed.append(file_path)
+
+    if check_changes and files_changed:
+        raise RuntimeError(
+            f"The following files were modified during the run:\n"
+            + "\n".join(str(file) for file in files_changed)
+        )
+
+
+if __name__ == "__main__":
+    import sys
+
+    path = sys.argv[1] if len(sys.argv) > 1 else MDX_DIR
+    line_length = int(sys.argv[2]) if len(sys.argv) > 2 else DEFAULT_LINE_LENGTH
+    check_changes = os.getenv("CI") == "true"  # Set to True in CI pipeline
+
+    if Path(path).is_dir():
+        process_mdx_files(path, FILE_PATTERN, line_length, check_changes)
+    elif Path(path).is_file():
+        if FILE_PATTERN.search(path):
+            process_mdx_files(Path(path).parent, FILE_PATTERN, line_length, check_changes)
+        else:
+            print("The specified file does not match the MDX pattern.")
+    else:
+        print("Provided path is not valid.")

.github/workflows/check-python-code-snippets.yml

@@ -0,0 +1,39 @@
+name: check-python-code-snippets
+
+on:
+  pull_request:
+    branches:
+      - main
+    paths:
+      - 'fern/pages/**/*.mdx'
+      - 'fern/pages/**/**/*.mdx'
+
+jobs:
+  run:
+    runs-on: ubuntu-latest
+    permissions: write-all
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.11'
+
+      - name: Install Poetry
+        shell: bash
+        run: |
+          pipx install poetry
+
+      - name: Install Project Dependencies with Poetry
+        shell: bash
+        run: |
+          poetry install
+
+      - name: Run Python MDX Snippet Formatter
+        shell: bash
+        env:
+          CI: true
+        run: poetry run python .github/scripts/check_python_code_snippets.py fern/pages

cohere-openapi.yaml

@@ -5962,6 +5962,15 @@ paths:
                     A list of available tools (functions) that the model may suggest invoking before producing a text response.
 
                     When `tools` is passed (without `tool_results`), the `text` content in the response will be empty and the `tool_calls` field in the response will be populated with a list of tool calls that need to be made. If no calls need to be made, the `tool_calls` array will be empty.
+                strict_tools:
+                  x-fern-audiences:
+                    - public
+                  x-fern-availability: beta
+                  type: boolean
+                  description: |
+                    When set to `true`, tool calls in the Assistant message will be forced to follow the tool definition strictly. Learn more in the [Strict Tools guide](https://docs.cohere.com/docs/structured-outputs-json#structured-outputs-tools).
+
+                    **Note**: The first few requests with a new set of tools will take longer to process.
                 documents:
                   type: array
                   items:
@@ -6037,7 +6046,7 @@ paths:
                   minimum: 0
                   maximum: 500
                   description: |
-                    Ensures that only the top `k` most likely tokens are considered for generation at each step. When `k` is set to `0`, k-sampling is disabled. 
+                    Ensures that only the top `k` most likely tokens are considered for generation at each step. When `k` is set to `0`, k-sampling is disabled.
                     Defaults to `0`, min value of `0`, max value of `500`.
                 p:
                   type: number

fern/pages/models/aya.mdx

@@ -1,6 +1,6 @@
 ---
 title: Aya Family of Models
-slug: aya/tools
+slug: "docs/aya"
 hidden: false
 description: >-
   Understand Cohere for AI's groundbreaking multilingual Aya models, which aim to bring many more languages into generative AI.
@@ -66,7 +66,7 @@ Espero que esta historia te sea útil para ilustrar vocabulario sencillo en espa
 Finally, you can directly download the raw models for research purposes because Cohere For AI has released [Aya Expanse 8B](https://huggingface.co/CohereForAI/aya-expanse-8b) and [Aya Expanse 32B](https://huggingface.co/CohereForAI/aya-expanse-32b) as open-weight models, through HuggingFace. What’s more, the massively multilingual instruction data used for development of these models has been [made available](https://huggingface.co/datasets/CohereForAI/aya_collection) for download as well.
 
 ## Find More
-We hope you’ve found this as fascinating as we do! If you want to see more substantial projects you can check out these notebooks (source):
+We hope you’ve found this as fascinating as we do! If you want to see more substantial projects you can check out these notebooks ([source](https://huggingface.co/CohereForAI/aya-expanse-32b)):
 
 - [Multilingual Writing Assistant](https://colab.research.google.com/drive/1SRLWQ0HdYN_NbRMVVUHTDXb-LSMZWF60)
 - [AyaMCooking](https://colab.research.google.com/drive/1-cnn4LXYoZ4ARBpnsjQM3sU7egOL_fLB?usp=sharing)

pyproject.toml

@@ -8,6 +8,7 @@ readme = "README.md"
 [tool.poetry.dependencies]
 python = "^3.11"
 cohere = "^5.11.1"
+black = "^24.10.0"
 
 
 [build-system]