klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[improvement]: Graph nodes extraction improved (#2035)

Browse Source
This commit is contained in:
Mayank
2024-11-21 12:27:39 +05:30
committed by GitHub
parent 62ca0ddbe2
commit 4b8e32830a
4 changed files with 171 additions and 142 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
mem0/graphs/utils.py
View File

@@ -18,50 +18,51 @@ Guidelines:
7. Relationship Refinement: Look for opportunities to refine relationship descriptions for greater precision or clarity.
8. Redundancy Elimination: Identify and merge any redundant or highly similar relationships that may result from the update.
Memory Format:
source -- RELATIONSHIP -- destination
Task Details:
- Existing Graph Memories:
======= Existing Graph Memories:=======
{existing_memories}
- New Graph Memory: {memory}
======= New Graph Memory:=======
{new_memories}
Output:
Provide a list of update instructions, each specifying the source, target, and the new relationship to be set. Only include memories that require updates.
"""
EXTRACT_ENTITIES_PROMPT = """
EXTRACT_RELATIONS_PROMPT = """
You are an advanced algorithm designed to extract structured information from text to construct knowledge graphs. Your goal is to capture comprehensive information while maintaining accuracy. Follow these key principles:
You are an advanced algorithm designed to extract structured information from text to construct knowledge graphs. Your goal is to capture comprehensive and accurate information. Follow these key principles:
1. Extract only explicitly stated information from the text.
2. Identify nodes (entities/concepts), their types, and relationships.
3. Use "USER_ID" as the source node for any self-references (I, me, my, etc.) in user messages.
2. Establish relationships among the entities provided.
3. Use "USER_ID" as the source entity for any self-references (e.g., "I," "me," "my," etc.) in user messages.
CUSTOM_PROMPT
Nodes and Types:
- Aim for simplicity and clarity in node representation.
- Use basic, general types for node labels (e.g. "person" instead of "mathematician").
Relationships:
- Use consistent, general, and timeless relationship types.
- Example: Prefer "PROFESSOR" over "BECAME_PROFESSOR".
- Use consistent, general, and timeless relationship types.
- Example: Prefer "PROFESSOR" over "BECAME_PROFESSOR."
- Relationships should only be established among the entities explicitly mentioned in the user message.
Entity Consistency:
- Use the most complete identifier for entities mentioned multiple times.
- Example: Always use "John Doe" instead of variations like "Joe" or pronouns.
- Ensure that relationships are coherent and logically align with the context of the message.
- Maintain consistent naming for entities across the extracted data.
Strive for a coherent, easily understandable knowledge graph by maintaining consistency in entity references and relationship types.
Strive to construct a coherent and easily understandable knowledge graph by eshtablishing all the relationships among the entities and adherence to the user’s context.
Adhere strictly to these guidelines to ensure high-quality knowledge graph extraction."""
def get_update_memory_prompt(existing_memories, memory, template):
return template.format(existing_memories=existing_memories, memory=memory)
def get_update_memory_prompt(existing_memories, new_memories, template):
return template.format(existing_memories=existing_memories, new_memories=new_memories)
def get_update_memory_messages(existing_memories, memory):
def get_update_memory_messages(existing_memories, new_memories):
return [
{
"role": "user",
"content": get_update_memory_prompt(existing_memories, memory, UPDATE_GRAPH_PROMPT),
"content": get_update_memory_prompt(existing_memories, new_memories, UPDATE_GRAPH_PROMPT),
},
]