Simple python example #177
Conversation
WalkthroughThe changes include updates to the Changes
Possibly related PRs
Suggested reviewers
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Outside diff range and nitpick comments (6)
examples/python/simple_example.py (3)
5-9: Enhance prerequisites with error handling guidance.The setup instructions are clear, but consider adding information about common errors and troubleshooting steps, such as what happens if the API key is invalid or if the
.envfile is not found.# Prerequisites: # 1. Copy `.env.template` and rename it to `.env`. # 2. Add your OpenAI API key to the `.env` file in the `LLM_API_KEY` field: # LLM_API_KEY = "your_key_here" -# 3. (Optional) To minimize setup effort, set `VECTOR_DB_PROVIDER="lancedb"` in `.env". +# 3. (Optional) To minimize setup effort, set `VECTOR_DB_PROVIDER="lancedb"` in `.env`. +# +# Common issues: +# - If you get an authentication error, verify your OpenAI API key is correct +# - If you get a configuration error, ensure the .env file exists in the root directory
38-39: Add proper shutdown handling for the async event loop.Consider adding signal handlers to ensure clean shutdown of the async operations.
+import signal + if __name__ == '__main__': - asyncio.run(main()) + try: + loop = asyncio.get_event_loop() + signals = (signal.SIGHUP, signal.SIGTERM, signal.SIGINT) + for s in signals: + loop.add_signal_handler( + s, lambda s=s: asyncio.create_task(loop.shutdown_asyncgens()) + ) + loop.run_until_complete(main()) + except KeyboardInterrupt: + print("\nShutting down gracefully...") + finally: + loop.close()
1-1: Add comprehensive module documentation.As this is an example file, it should include a detailed module docstring explaining its purpose, usage, and expected output.
+"""Example script demonstrating basic usage of the cognee library. + +This script shows how to: +1. Set up and configure cognee +2. Add text to the knowledge base +3. Create a knowledge graph +4. Query for insights + +Example usage: + $ python simple_example.py + +Expected output: + Adding text to cognee... + Text added successfully + Creating knowledge graph... + Knowledge graph created successfully + + Searching for insights... + Search Results: + -------------------------------------------------- + 1. [Search results will appear here] + -------------------------------------------------- +""" + import cogneeREADME.md (3)
99-102: Add path information for .env.template.The setup instructions should specify where to find the
.env.templatefile. Consider adding the repository root path or a link to the template file in the repository.-First, copy `.env.template` to `.env` and add your OpenAI API key to the LLM_API_KEY field. +First, copy the `.env.template` file from the repository root to `.env` and add your OpenAI API key to the LLM_API_KEY field.
105-130: Consider enhancing the example with error handling and type hints.The example effectively demonstrates the basic workflow. However, consider these improvements for production readiness:
- Add error handling for potential API failures
- Include type hints for better code clarity
- Show how to handle missing API key gracefully
Here's a suggested enhancement:
import cognee import asyncio from cognee.api.v1.search import SearchType +from typing import List, Optional -async def main(): +async def main() -> None: await cognee.prune.prune_data() # Reset cognee data await cognee.prune.prune_system(metadata=True) # Reset cognee system state text = """ Natural language processing (NLP) is an interdisciplinary subfield of computer science and information retrieval. """ - await cognee.add(text) # Add text to cognee - await cognee.cognify() # Use LLMs and cognee to create knowledge graph + try: + await cognee.add(text) # Add text to cognee + await cognee.cognify() # Use LLMs and cognee to create knowledge graph - search_results = await cognee.search( # Search cognee for insights - SearchType.INSIGHTS, - {'query': 'Tell me about NLP'} - ) + search_results: List[str] = await cognee.search( # Search cognee for insights + SearchType.INSIGHTS, + {'query': 'Tell me about NLP'} + ) - for result_text in search_results: # Display results - print(result_text) + for result_text in search_results: # Display results + print(result_text) + except Exception as e: + print(f"An error occurred: {e}") + raise
132-132: Fix typo in path.There's a typo in the word "python" in the example path.
-A version of this example is here: `examples/pyton/simple_example.py` +A version of this example is here: `examples/python/simple_example.py`
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
📒 Files selected for processing (2)
README.md(1 hunks)examples/python/simple_example.py(1 hunks)
🔇 Additional comments (1)
README.md (1)
103-104: LGTM!
Clear and concise introduction to the example.
| async def main(): | ||
| # Create a clean slate for cognee -- reset data and system state | ||
| await cognee.prune.prune_data() | ||
| await cognee.prune.prune_system(metadata=True) |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add error handling and type hints to the main function.
The reset operations could fail and should be wrapped in try-except blocks. Additionally, adding type hints would improve code clarity.
-async def main():
+async def main() -> None:
# Create a clean slate for cognee -- reset data and system state
- await cognee.prune.prune_data()
- await cognee.prune.prune_system(metadata=True)
+ try:
+ await cognee.prune.prune_data()
+ await cognee.prune.prune_system(metadata=True)
+ except Exception as e:
+ print(f"Failed to reset cognee state: {e}")
+ raise📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| async def main(): | |
| # Create a clean slate for cognee -- reset data and system state | |
| await cognee.prune.prune_data() | |
| await cognee.prune.prune_system(metadata=True) | |
| async def main() -> None: | |
| # Create a clean slate for cognee -- reset data and system state | |
| try: | |
| await cognee.prune.prune_data() | |
| await cognee.prune.prune_system(metadata=True) | |
| except Exception as e: | |
| print(f"Failed to reset cognee state: {e}") | |
| raise |
| # Query cognee for insights on the added text | ||
| search_results = await cognee.search( | ||
| SearchType.INSIGHTS, | ||
| {'query': 'Tell me about NLP'} | ||
| ) | ||
|
|
||
| # Display search results | ||
| for result_text in search_results: | ||
| print(result_text) |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Enhance search functionality with error handling and improved results display.
The search operation needs error handling, and the results display could be more user-friendly with proper formatting.
# Query cognee for insights on the added text
- search_results = await cognee.search(
- SearchType.INSIGHTS,
- {'query': 'Tell me about NLP'}
- )
+ try:
+ print("\nSearching for insights...")
+ search_results = await cognee.search(
+ SearchType.INSIGHTS,
+ {'query': 'Tell me about NLP'}
+ )
- # Display search results
- for result_text in search_results:
- print(result_text)
+ # Display search results
+ if not search_results:
+ print("No results found")
+ else:
+ print("\nSearch Results:")
+ print("-" * 50)
+ for i, result_text in enumerate(search_results, 1):
+ print(f"\n{i}. {result_text}")
+ print("-" * 50)
+ except Exception as e:
+ print(f"Search failed: {e}")
+ raise📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| # Query cognee for insights on the added text | |
| search_results = await cognee.search( | |
| SearchType.INSIGHTS, | |
| {'query': 'Tell me about NLP'} | |
| ) | |
| # Display search results | |
| for result_text in search_results: | |
| print(result_text) | |
| # Query cognee for insights on the added text | |
| try: | |
| print("\nSearching for insights...") | |
| search_results = await cognee.search( | |
| SearchType.INSIGHTS, | |
| {'query': 'Tell me about NLP'} | |
| ) | |
| # Display search results | |
| if not search_results: | |
| print("No results found") | |
| else: | |
| print("\nSearch Results:") | |
| print("-" * 50) | |
| for i, result_text in enumerate(search_results, 1): | |
| print(f"\n{i}. {result_text}") | |
| print("-" * 50) | |
| except Exception as e: | |
| print(f"Search failed: {e}") | |
| raise |
| # cognee knowledge graph will be created based on this text | ||
| text = """ | ||
| Natural language processing (NLP) is an interdisciplinary | ||
| subfield of computer science and information retrieval. | ||
| """ | ||
|
|
||
| # Add the text, and make it available for cognify | ||
| await cognee.add(text) | ||
|
|
||
| # Use LLMs and cognee to create knowledge graph | ||
| await cognee.cognify() |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add error handling and progress feedback for text processing.
The text processing operations should include error handling and provide feedback about the processing status to improve user experience.
# cognee knowledge graph will be created based on this text
text = """
Natural language processing (NLP) is an interdisciplinary
subfield of computer science and information retrieval.
"""
# Add the text, and make it available for cognify
- await cognee.add(text)
+ try:
+ print("Adding text to cognee...")
+ await cognee.add(text)
+ print("Text added successfully")
- # Use LLMs and cognee to create knowledge graph
- await cognee.cognify()
+ print("Creating knowledge graph...")
+ await cognee.cognify()
+ print("Knowledge graph created successfully")
+ except Exception as e:
+ print(f"Failed to process text: {e}")
+ raise📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| # cognee knowledge graph will be created based on this text | |
| text = """ | |
| Natural language processing (NLP) is an interdisciplinary | |
| subfield of computer science and information retrieval. | |
| """ | |
| # Add the text, and make it available for cognify | |
| await cognee.add(text) | |
| # Use LLMs and cognee to create knowledge graph | |
| await cognee.cognify() | |
| # cognee knowledge graph will be created based on this text | |
| text = """ | |
| Natural language processing (NLP) is an interdisciplinary | |
| subfield of computer science and information retrieval. | |
| """ | |
| # Add the text, and make it available for cognify | |
| try: | |
| print("Adding text to cognee...") | |
| await cognee.add(text) | |
| print("Text added successfully") | |
| print("Creating knowledge graph...") | |
| await cognee.cognify() | |
| print("Knowledge graph created successfully") | |
| except Exception as e: | |
| print(f"Failed to process text: {e}") | |
| raise |
Summary by CodeRabbit
New Features
README.mdwith clearer usage instructions and examples for thecogneelibrary.simple_example.py) demonstrating the library's functionality for NLP tasks.Bug Fixes