graphiti/core/utils/maintenance/node_operations.py

155 lines
4.7 KiB
Python
Raw Normal View History

import logging
from datetime import datetime
from time import time
from core.llm_client import LLMClient
from core.nodes import EntityNode, EpisodicNode
from core.prompts import prompt_library
logger = logging.getLogger(__name__)
async def extract_nodes(
llm_client: LLMClient,
episode: EpisodicNode,
previous_episodes: list[EpisodicNode],
) -> list[EntityNode]:
start = time()
# Prepare context for LLM
context = {
'episode_content': episode.content,
'episode_timestamp': (episode.valid_at.isoformat() if episode.valid_at else None),
'previous_episodes': [
{
'content': ep.content,
'timestamp': ep.valid_at.isoformat() if ep.valid_at else None,
}
for ep in previous_episodes
],
}
llm_response = await llm_client.generate_response(prompt_library.extract_nodes.v3(context))
new_nodes_data = llm_response.get('new_nodes', [])
end = time()
logger.info(f'Extracted new nodes: {new_nodes_data} in {(end - start) * 1000} ms')
# Convert the extracted data into EntityNode objects
new_nodes = []
for node_data in new_nodes_data:
new_node = EntityNode(
name=node_data['name'],
labels=node_data['labels'],
summary=node_data['summary'],
created_at=datetime.now(),
)
new_nodes.append(new_node)
logger.info(f'Created new node: {new_node.name} (UUID: {new_node.uuid})')
return new_nodes
async def dedupe_extracted_nodes(
llm_client: LLMClient,
extracted_nodes: list[EntityNode],
existing_nodes: list[EntityNode],
) -> tuple[list[EntityNode], dict[str, str], list[EntityNode]]:
start = time()
# build existing node map
node_map: dict[str, EntityNode] = {}
for node in existing_nodes:
node_map[node.name] = node
# Temp hack
new_nodes_map: dict[str, EntityNode] = {}
for node in extracted_nodes:
new_nodes_map[node.name] = node
# Prepare context for LLM
existing_nodes_context = [
{'name': node.name, 'summary': node.summary} for node in existing_nodes
]
extracted_nodes_context = [
{'name': node.name, 'summary': node.summary} for node in extracted_nodes
]
context = {
'existing_nodes': existing_nodes_context,
'extracted_nodes': extracted_nodes_context,
}
llm_response = await llm_client.generate_response(prompt_library.dedupe_nodes.v2(context))
duplicate_data = llm_response.get('duplicates', [])
end = time()
logger.info(f'Deduplicated nodes: {duplicate_data} in {(end - start) * 1000} ms')
uuid_map: dict[str, str] = {}
for duplicate in duplicate_data:
uuid = new_nodes_map[duplicate['name']].uuid
uuid_value = node_map[duplicate['duplicate_of']].uuid
uuid_map[uuid] = uuid_value
nodes: list[EntityNode] = []
brand_new_nodes: list[EntityNode] = []
for node in extracted_nodes:
if node.uuid in uuid_map:
existing_uuid = uuid_map[node.uuid]
# TODO(Preston): This is a bit of a hack I implemented because we were getting incorrect uuids for existing nodes,
# can you revisit the node dedup function and make it somewhat cleaner and add more comments/tests please?
# find an existing node by the uuid from the nodes_map (each key is name, so we need to iterate by uuid value)
existing_node = next((v for k, v in node_map.items() if v.uuid == existing_uuid), None)
if existing_node:
nodes.append(existing_node)
continue
brand_new_nodes.append(node)
nodes.append(node)
return nodes, uuid_map, brand_new_nodes
async def dedupe_node_list(
llm_client: LLMClient,
nodes: list[EntityNode],
) -> tuple[list[EntityNode], dict[str, str]]:
start = time()
# build node map
node_map = {}
for node in nodes:
node_map[node.name] = node
# Prepare context for LLM
nodes_context = [{'name': node.name, 'summary': node.summary} for node in nodes]
context = {
'nodes': nodes_context,
}
llm_response = await llm_client.generate_response(
prompt_library.dedupe_nodes.node_list(context)
)
nodes_data = llm_response.get('nodes', [])
end = time()
logger.info(f'Deduplicated nodes: {nodes_data} in {(end - start) * 1000} ms')
# Get full node data
unique_nodes = []
uuid_map: dict[str, str] = {}
for node_data in nodes_data:
node = node_map[node_data['names'][0]]
unique_nodes.append(node)
for name in node_data['names'][1:]:
uuid = node_map[name].uuid
uuid_value = node_map[node_data['names'][0]].uuid
uuid_map[uuid] = uuid_value
return unique_nodes, uuid_map