5fe7ff9883
<!-- .github/pull_request_template.md --> ## Description Refactor search so query type doesn't need to be provided to make it simpler for new users ## DCO Affirmation I affirm that all code in every commit of this pull request conforms to the terms of the Topoteretes Developer Certificate of Origin <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **Refactor** - Improved the search interface by standardizing parameter usage with explicit keyword arguments for specifying search types, enhancing clarity and consistency. - **Tests** - Updated test cases and example integrations to align with the revised search parameters, ensuring consistent behavior and reliable validation of search outcomes. <!-- end of auto-generated comment: release notes by coderabbit.ai -->
77 lines
3.5 KiB
Python
77 lines
3.5 KiB
Python
import asyncio
|
|
import cognee
|
|
import logging
|
|
from cognee.api.v1.search import SearchType
|
|
from cognee.shared.utils import setup_logging
|
|
|
|
# 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"
|
|
|
|
|
|
async def main():
|
|
# Create a clean slate for cognee -- reset data and system state
|
|
print("Resetting cognee data...")
|
|
await cognee.prune.prune_data()
|
|
await cognee.prune.prune_system(metadata=True)
|
|
print("Data reset complete.\n")
|
|
|
|
# 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.
|
|
"""
|
|
|
|
print("Adding text to cognee:")
|
|
print(text.strip())
|
|
# Add the text, and make it available for cognify
|
|
await cognee.add(text)
|
|
print("Text added successfully.\n")
|
|
|
|
print("Running cognify to create knowledge graph...\n")
|
|
print("Cognify process steps:")
|
|
print("1. Classifying the document: Determining the type and category of the input text.")
|
|
print(
|
|
"2. Checking permissions: Ensuring the user has the necessary rights to process the text."
|
|
)
|
|
print(
|
|
"3. Extracting text chunks: Breaking down the text into sentences or phrases for analysis."
|
|
)
|
|
print("4. Adding data points: Storing the extracted chunks for processing.")
|
|
print(
|
|
"5. Generating knowledge graph: Extracting entities and relationships to form a knowledge graph."
|
|
)
|
|
print("6. Summarizing text: Creating concise summaries of the content for quick insights.\n")
|
|
|
|
# Use LLMs and cognee to create knowledge graph
|
|
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
|
|
search_results = await cognee.search(query_type=SearchType.INSIGHTS, query_text=query_text)
|
|
|
|
print("Search results:")
|
|
# Display results
|
|
for result_text in search_results:
|
|
print(result_text)
|
|
|
|
# Example output:
|
|
# ({'id': UUID('bc338a39-64d6-549a-acec-da60846dd90d'), 'updated_at': datetime.datetime(2024, 11, 21, 12, 23, 1, 211808, tzinfo=datetime.timezone.utc), 'name': 'natural language processing', 'description': 'An interdisciplinary subfield of computer science and information retrieval.'}, {'relationship_name': 'is_a_subfield_of', 'source_node_id': UUID('bc338a39-64d6-549a-acec-da60846dd90d'), 'target_node_id': UUID('6218dbab-eb6a-5759-a864-b3419755ffe0'), 'updated_at': datetime.datetime(2024, 11, 21, 12, 23, 15, 473137, tzinfo=datetime.timezone.utc)}, {'id': UUID('6218dbab-eb6a-5759-a864-b3419755ffe0'), 'updated_at': datetime.datetime(2024, 11, 21, 12, 23, 1, 211808, tzinfo=datetime.timezone.utc), 'name': 'computer science', 'description': 'The study of computation and information processing.'})
|
|
# (...)
|
|
# It represents nodes and relationships in the knowledge graph:
|
|
# - The first element is the source node (e.g., 'natural language processing').
|
|
# - The second element is the relationship between nodes (e.g., 'is_a_subfield_of').
|
|
# - The third element is the target node (e.g., 'computer science').
|
|
|
|
|
|
if __name__ == "__main__":
|
|
setup_logging(logging.ERROR)
|
|
loop = asyncio.new_event_loop()
|
|
asyncio.set_event_loop(loop)
|
|
try:
|
|
loop.run_until_complete(main())
|
|
finally:
|
|
loop.run_until_complete(loop.shutdown_asyncgens())
|