gmakstutis/cognee
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: add print statements to the simple example, update README

Browse source
This commit is contained in:
hande-k 2024-11-20 08:47:02 +01:00
parent 2331739e07
commit c6e447f28c
2 changed files with 34 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
README.md
View file

@ -105,37 +105,47 @@ import asyncio
from cognee.api.v1.search import SearchType from cognee.api.v1.search import SearchType
async def main(): async def main():
# Reset cognee data # Create a clean slate for cognee -- reset data and system state
print("Resetting cognee data...")
await cognee.prune.prune_data() await cognee.prune.prune_data()
# Reset cognee system state
await cognee.prune.prune_system(metadata=True) await cognee.prune.prune_system(metadata=True)
print("Data reset complete.\n")
# cognee knowledge graph will be created based on this text
text = """ text = """
Natural language processing (NLP) is an interdisciplinary Natural language processing (NLP) is an interdisciplinary
subfield of computer science and information retrieval. subfield of computer science and information retrieval.
""" """
print("Adding text to cognee:")
# Add text to cognee print(text.strip())
await cognee.add(text) await cognee.add(text)
print("Text added successfully.\n")
# Use LLMs and cognee to create knowledge graph # Use LLMs and cognee to create knowledge graph
print("Running cognify to create knowledge graph...")
await cognee.cognify() await cognee.cognify()
print("Cognify process complete.\n")
# Search cognee for insights # Query cognee for insights on the added text
query_text = 'Tell me about NLP'
print(f"Searching cognee for insights with query: '{query_text}'")
search_results = await cognee.search( search_results = await cognee.search(
SearchType.INSIGHTS, SearchType.INSIGHTS,
"Tell me about NLP", query_text=query_text,
) )
# Display results # Display search results
print("Search results:")
for result_text in search_results: for result_text in search_results:
print(result_text) print(result_text)
# Expected output:
# natural_language_processing is_a field # natural_language_processing is_a field
# natural_language_processing is_subfield_of computer_science # natural_language_processing is_subfield_of computer_science
# natural_language_processing is_subfield_of information_retrieval # natural_language_processing is_subfield_of information_retrieval
asyncio.run(main()) asyncio.run(main())
``` ```
When you run this script, you will see step-by-step messages in the console that help you trace the execution flow and understand what the script is doing at each stage.
A version of this example is here: `examples/python/simple_example.py` A version of this example is here: `examples/python/simple_example.py`
### Create your own memory store ### Create your own memory store

21
examples/python/simple_example.py
View file

@ -11,29 +11,42 @@ from cognee.api.v1.search import SearchType
async def main(): async def main():
# Create a clean slate for cognee -- reset data and system state # Create a clean slate for cognee -- reset data and system state
print("Resetting cognee data...")
await cognee.prune.prune_data() await cognee.prune.prune_data()
await cognee.prune.prune_system(metadata=True) await cognee.prune.prune_system(metadata=True)
print("Data reset complete.\n")
# cognee knowledge graph will be created based on this text # cognee knowledge graph will be created based on this text
text = """ text = """
Natural language processing (NLP) is an interdisciplinary Natural language processing (NLP) is an interdisciplinary
subfield of computer science and information retrieval. subfield of computer science and information retrieval.
""" """
print("Adding text to cognee:")
print(text.strip())
# Add the text, and make it available for cognify # Add the text, and make it available for cognify
await cognee.add(text) await cognee.add(text)
print("Text added successfully.\n")
print("Running cognify to create knowledge graph...")
# Use LLMs and cognee to create knowledge graph # Use LLMs and cognee to create knowledge graph
await cognee.cognify() await cognee.cognify()
print("Cognify process complete.\n")
query_text = 'Tell me about NLP'
print(f"Searching cognee for insights with query: '{query_text}'")
# Query cognee for insights on the added text # Query cognee for insights on the added text
search_results = await cognee.search( search_results = await cognee.search(
SearchType.INSIGHTS, query_text='Tell me about NLP' SearchType.INSIGHTS, query_text=query_text
) )
# Display search results print("Search results:")
# Display results
for result_text in search_results: for result_text in search_results:
print(result_text) print(result_text)
if __name__ == '__main__': if __name__ == '__main__':
asyncio.run(main()) asyncio.run(main())