Add comprehensive documentation and code comments

This commit adds extensive documentation to the Mistral OCR CLI project:

- Add API.md with detailed API response format documentation
- Add CHANGELOG.md to track version changes
- Add CONTRIBUTING.md with guidelines for contributors
- Enhance README.md with more detailed usage examples and troubleshooting
- Add proper docstrings to all Python modules and functions
- Update requirements.txt with development dependencies
- Improve setup.py with better metadata

These changes make the project more accessible to users and contributors.

mistral_ocr/client.py

@@ -5,10 +5,33 @@ import requests
 from typing import Optional, Dict, Any, Tuple
 
 class MistralClient:
+    """
+    Client for interacting with the Mistral AI OCR API.
+    
+    This client handles authentication, file uploads, and OCR processing
+    requests to the Mistral AI API.
+    
+    Attributes:
+        BASE_URL (str): Base URL for the Mistral AI API
+        MAX_FILE_SIZE (int): Maximum allowed file size in bytes (52 MB)
+        api_key (str): Mistral AI API key for authentication
+        session (requests.Session): Session object for making HTTP requests
+    """
+    
     BASE_URL = "https://api.mistral.ai/v1"
     MAX_FILE_SIZE = 52 * 1024 * 1024  # 52 MB
     
     def __init__(self, api_key: Optional[str] = None):
+        """
+        Initialize the Mistral AI client.
+        
+        Args:
+            api_key (Optional[str]): Mistral AI API key. If not provided,
+                                    will look for MISTRAL_API_KEY environment variable.
+                                    
+        Raises:
+            ValueError: If no API key is provided or found in environment variables.
+        """
         self.api_key = api_key or os.environ.get("MISTRAL_API_KEY")
         if not self.api_key:
             raise ValueError("API key must be provided or set as MISTRAL_API_KEY environment variable")
@@ -20,7 +43,19 @@ class MistralClient:
         })
     
     def upload_file(self, file_path: str) -> str:
-        """Upload a file to Mistral API for OCR processing."""
+        """
+        Upload a file to Mistral API for OCR processing.
+        
+        Args:
+            file_path (str): Path to the local file to upload
+            
+        Returns:
+            str: File ID returned by the API
+            
+        Raises:
+            ValueError: If the file is too large or if the upload fails
+            requests.RequestException: If there's an error communicating with the API
+        """
         # Check file size
         file_size = os.path.getsize(file_path)
         if file_size > self.MAX_FILE_SIZE:
@@ -72,7 +107,19 @@ class MistralClient:
         raise last_error or ValueError(f"Failed to upload file after {max_retries} attempts")
     
     def get_file_url(self, file_id: str) -> str:
-        """Get a signed URL for an uploaded file."""
+        """
+        Get a signed URL for an uploaded file.
+        
+        Args:
+            file_id (str): ID of the file previously uploaded to the API
+            
+        Returns:
+            str: Signed URL that can be used for OCR processing
+            
+        Raises:
+            ValueError: If the API response does not contain a URL
+            requests.RequestException: If there's an error communicating with the API
+        """
         response = self.session.get(f"{self.BASE_URL}/files/{file_id}/url?expiry=24")
         response.raise_for_status()
         
@@ -85,7 +132,22 @@ class MistralClient:
         return url
     
     def process_ocr(self, doc_type: str, doc_source: str, include_image_base64: bool = False) -> bytes:
-        """Process a document with OCR."""
+        """
+        Process a document with OCR.
+        
+        Args:
+            doc_type (str): Type of document, either "document_url" or "image_url"
+            doc_source (str): URL of the document to process
+            include_image_base64 (bool, optional): Whether to include base64-encoded 
+                                                  images in the response. Defaults to False.
+            
+        Returns:
+            bytes: JSON response from the API containing OCR results
+            
+        Raises:
+            ValueError: If the document type is unsupported or if processing fails
+            requests.RequestException: If there's an error communicating with the API
+        """
         if doc_type not in ["document_url", "image_url"]:
             raise ValueError(f"Unsupported document type: {doc_type}")