update readme examples

Author: zachary62

README.md

@@ -16,7 +16,7 @@
 
 This is a tutorial project of [Pocket Flow](https://github.com/The-Pocket/PocketFlow), a 100-line LLM framework. It crawls GitHub repositories and build a knowledge base from the code. It analyzes entire codebases to identify core abstractions and how they interact, and transforms complex code into beginner-friendly tutorials with clear visualizations.
 
-## Example Tutorials for Popular GitHub Repositories!
+## ⭐ Example Tutorials for Popular GitHub Repositories!
 
 - [AutoGen Core](https://the-pocket.github.io/Tutorial-Codebase-Knowledge/AutoGen%20Core) - Build AI teams that talk, think, and solve problems together like coworkers!
 

flow.py

@@ -1,14 +1,33 @@
 from pocketflow import Flow
-from nodes import GetQuestionNode, AnswerNode
-
-def create_qa_flow():
-    """Create and return a question-answering flow."""
-    # Create nodes
-    get_question_node = GetQuestionNode()
-    answer_node = AnswerNode()
-    
-    # Connect nodes in sequence
-    get_question_node >> answer_node
-    
-    # Create flow starting with input node
-    return Flow(start=get_question_node)
+# Import all node classes from nodes.py
+from nodes import (
+    FetchRepo,
+    IdentifyAbstractions,
+    AnalyzeRelationships,
+    OrderChapters,
+    WriteChapters,
+    CombineTutorial
+)
+
+def create_tutorial_flow():
+    """Creates and returns the codebase tutorial generation flow."""
+
+    # Instantiate nodes
+    fetch_repo = FetchRepo()
+    identify_abstractions = IdentifyAbstractions(max_retries=3, wait=10)
+    analyze_relationships = AnalyzeRelationships(max_retries=3, wait=10)
+    order_chapters = OrderChapters(max_retries=3, wait=10)
+    write_chapters = WriteChapters(max_retries=3, wait=10) # This is a BatchNode
+    combine_tutorial = CombineTutorial()
+
+    # Connect nodes in sequence based on the design
+    fetch_repo >> identify_abstractions
+    identify_abstractions >> analyze_relationships
+    analyze_relationships >> order_chapters
+    order_chapters >> write_chapters
+    write_chapters >> combine_tutorial
+
+    # Create the flow starting with FetchRepo
+    tutorial_flow = Flow(start=fetch_repo)
+
+    return tutorial_flow

main.py

@@ -1,16 +1,67 @@
-from flow import qa_flow
+import os
+import argparse
+# Import the function that creates the flow
+from flow import create_tutorial_flow
 
-# Example main function
-# Please replace this with your own main function
+# Default file patterns
+DEFAULT_INCLUDE_PATTERNS = {
+    "*.py", "*.js", "*.ts", "*.go", "*.java", "*.pyi", "*.pyx", 
+    "*.c", "*.cc", "*.cpp", "*.h", "*.md", "*.rst", "Dockerfile", 
+    "Makefile", "*.yaml", "*.yml"
+}
+
+DEFAULT_EXCLUDE_PATTERNS = {
+    "*test*", "tests/*", "docs/*", "examples/*", "v1/*", 
+    "dist/*", "build/*", "experimental/*", "deprecated/*", 
+    "legacy/*", ".git/*", ".github/*"
+}
+
+# --- Main Function ---
 def main():
+    parser = argparse.ArgumentParser(description="Generate a tutorial for a GitHub codebase.")
+    parser.add_argument("repo_url", help="URL of the public GitHub repository.")
+    parser.add_argument("-n", "--name", help="Project name (optional, derived from URL if omitted).")
+    parser.add_argument("-t", "--token", help="GitHub personal access token (optional, reads from GITHUB_TOKEN env var if not provided).")
+    parser.add_argument("-o", "--output", default="output", help="Base directory for output (default: ./output).")
+    parser.add_argument("-i", "--include", nargs="+", help="Include file patterns (e.g. '*.py' '*.js'). Defaults to common code files if not specified.")
+    parser.add_argument("-e", "--exclude", nargs="+", help="Exclude file patterns (e.g. 'tests/*' 'docs/*'). Defaults to test/build directories if not specified.")
+    parser.add_argument("-s", "--max-size", type=int, default=100000, help="Maximum file size in bytes (default: 100000, about 100KB).")
+
+    args = parser.parse_args()
+
+    # Get GitHub token from argument or environment variable
+    github_token = args.token or os.environ.get('GITHUB_TOKEN')
+    if not github_token:
+        print("Warning: No GitHub token provided. You might hit rate limits for public repositories.")
+
+    # Initialize the shared dictionary with inputs
     shared = {
-        "question": "In one sentence, what's the end of universe?",
-        "answer": None
+        "repo_url": args.repo_url,
+        "project_name": args.name, # Can be None, FetchRepo will derive it
+        "github_token": github_token,
+        "output_dir": args.output, # Base directory for CombineTutorial output
+
+        # Add include/exclude patterns and max file size
+        "include_patterns": set(args.include) if args.include else DEFAULT_INCLUDE_PATTERNS,
+        "exclude_patterns": set(args.exclude) if args.exclude else DEFAULT_EXCLUDE_PATTERNS,
+        "max_file_size": args.max_size,
+
+        # Outputs will be populated by the nodes
+        "files": [],
+        "abstractions": [],
+        "relationships": {},
+        "chapter_order": [],
+        "chapters": [],
+        "final_output_dir": None
     }
 
-    qa_flow.run(shared)
-    print("Question:", shared["question"])
-    print("Answer:", shared["answer"])
+    print(f"Starting tutorial generation for: {args.repo_url}")
+
+    # Create the flow instance
+    tutorial_flow = create_tutorial_flow()
 
+    # Run the flow
+    tutorial_flow.run(shared)
+    
 if __name__ == "__main__":
     main()