🔍 Code Extractor

A dataclass that stores a reference to a previous conversation exchange, including metadata about the reference type, content, and relevance.

Purpose

ConversationReference serves as a structured data container for tracking and referencing previous exchanges in a conversation. It enables conversation continuity by storing key information about past interactions including the exchange identifier, type of reference (topic, solution, question, or data), the actual content being referenced, contextual snippets, and a relevance score for ranking or filtering purposes. This is typically used in conversational AI systems, chatbots, or dialogue management systems to maintain context and enable coherent multi-turn conversations.

Source Code

class ConversationReference:
    """Reference to a previous exchange"""
    exchange_number: int
    exchange_id: str
    reference_type: str  # 'topic', 'solution', 'question', 'data'
    referenced_content: str
    context_snippet: str
    relevance_score: float

Parameters

Parameter Details

exchange_number: An integer representing the sequential position of the exchange in the conversation history. Used for ordering and identifying specific exchanges chronologically.

exchange_id: A unique string identifier for the specific exchange being referenced. Allows for precise lookup and retrieval of the original exchange.

reference_type: A string categorizing the type of reference. Expected values are 'topic', 'solution', 'question', or 'data'. This helps classify what aspect of the previous exchange is being referenced.

referenced_content: A string containing the actual content from the previous exchange that is being referenced. This is the substantive information being recalled.

context_snippet: A string providing a brief excerpt or summary of the surrounding context from the referenced exchange. Helps understand the reference without retrieving the full exchange.

relevance_score: A float value (typically between 0.0 and 1.0) indicating how relevant this reference is to the current context. Higher scores indicate greater relevance, useful for ranking or filtering references.

Return Value

Instantiation returns a ConversationReference object with all six attributes initialized. As a dataclass, it automatically generates __init__, __repr__, __eq__, and other special methods. The object serves as an immutable-by-convention data container for conversation reference metadata.

Class Interface

Methods

Attributes

Required Imports

from dataclasses import dataclass

Usage Example

from dataclasses import dataclass

@dataclass
class ConversationReference:
    exchange_number: int
    exchange_id: str
    reference_type: str
    referenced_content: str
    context_snippet: str
    relevance_score: float

# Create a reference to a previous exchange
ref = ConversationReference(
    exchange_number=5,
    exchange_id="conv_123_ex_5",
    reference_type="solution",
    referenced_content="To solve this, use the formula: x = (a + b) / 2",
    context_snippet="User asked about calculating averages",
    relevance_score=0.92
)

# Access attributes
print(ref.exchange_number)  # 5
print(ref.reference_type)   # 'solution'
print(ref.relevance_score)  # 0.92

# Dataclass provides automatic __repr__
print(ref)

# Dataclass provides automatic equality comparison
ref2 = ConversationReference(5, "conv_123_ex_5", "solution", "To solve this, use the formula: x = (a + b) / 2", "User asked about calculating averages", 0.92)
print(ref == ref2)  # True

Best Practices

• Use meaningful exchange_id values that can be traced back to the original conversation storage system
• Ensure reference_type values are consistent across the application (use constants or enums for the four types: 'topic', 'solution', 'question', 'data')
• Normalize relevance_score to a consistent range (typically 0.0 to 1.0) for easier comparison and filtering
• Keep context_snippet concise but informative - it should provide enough context without requiring full exchange retrieval
• Consider making the class frozen (frozen=True) if immutability is desired after creation
• When storing multiple references, sort by relevance_score descending to prioritize most relevant references
• Validate that exchange_number is non-negative and exchange_id is non-empty when creating instances
• Use this class in conjunction with conversation management systems that maintain full exchange history

Tags

Similar Components

AI-powered semantic similarity - components with related functionality:

• class ConversationContext 74.7% similar

  A dataclass that stores comprehensive conversation context including timeline, turns, topics, insights, and references for managing rich conversational state.

  From: /tf/active/vicechatdev/e-ink-llm/conversation_context.py

• class Exchange 71.4% similar

  A dataclass representing a single exchange (input-response pair) in a conversation, storing metadata about the interaction including timing, tokens, and file information.

  From: /tf/active/vicechatdev/e-ink-llm/session_manager.py

• class ConversationState 67.4% similar

  A dataclass that represents the complete state of a conversation, including its metadata, exchanges, and lifecycle information.

  From: /tf/active/vicechatdev/e-ink-llm/session_manager.py

• class ConversationTurn 64.9% similar

  A dataclass representing a single turn in a conversation, storing metadata about the exchange including input/output summaries, files, topics, and processing metrics.

  From: /tf/active/vicechatdev/e-ink-llm/conversation_context.py

• class ConversationContextManager 59.4% similar

  Advanced conversation context manager that analyzes conversation history, extracts topics, builds reference maps, and generates contextual intelligence for multi-turn conversations.

  From: /tf/active/vicechatdev/e-ink-llm/conversation_context.py