updated documentation

lightrag/base.py

@@ -27,31 +27,54 @@ T = TypeVar("T")
 
 @dataclass
 class QueryParam:
-    mode: Literal["local", "global", "hybrid", "naive", "mix"] = "global"
+    """Configuration parameters for query execution in LightRAG."""
-    only_need_context: bool = False
-    only_need_prompt: bool = False
-    response_type: str = "Multiple Paragraphs"
-    stream: bool = False
-    # Number of top-k items to retrieve; corresponds to entities in "local" mode and relationships in "global" mode.
-    top_k: int = int(os.getenv("TOP_K", "60"))
-    # Number of document chunks to retrieve.
-    # top_n: int = 10
-    # Number of tokens for the original chunks.
-    max_token_for_text_unit: int = 4000
-    # Number of tokens for the relationship descriptions
-    max_token_for_global_context: int = 4000
-    # Number of tokens for the entity descriptions
-    max_token_for_local_context: int = 4000
-    hl_keywords: list[str] = field(default_factory=list)
-    ll_keywords: list[str] = field(default_factory=list)
-    # Conversation history support
-    conversation_history: list[dict[str, str]] = field(
-        default_factory=list
-    )  # Format: [{"role": "user/assistant", "content": "message"}]
-    history_turns: int = (
-        3  # Number of complete conversation turns (user-assistant pairs) to consider
-    )
 
+    mode: Literal["local", "global", "hybrid", "naive", "mix"] = "global"
+    """Specifies the retrieval mode:
+    - "local": Focuses on context-dependent information.
+    - "global": Utilizes global knowledge.
+    - "hybrid": Combines local and global retrieval methods.
+    - "naive": Performs a basic search without advanced techniques.
+    - "mix": Integrates knowledge graph and vector retrieval.
+    """
+
+    only_need_context: bool = False
+    """If True, only returns the retrieved context without generating a response."""
+
+    only_need_prompt: bool = False
+    """If True, only returns the generated prompt without producing a response."""
+
+    response_type: str = "Multiple Paragraphs"
+    """Defines the response format. Examples: 'Multiple Paragraphs', 'Single Paragraph', 'Bullet Points'."""
+
+    stream: bool = False
+    """If True, enables streaming output for real-time responses."""
+
+    top_k: int = int(os.getenv("TOP_K", "60"))
+    """Number of top items to retrieve. Represents entities in 'local' mode and relationships in 'global' mode."""
+
+    max_token_for_text_unit: int = 4000
+    """Maximum number of tokens allowed for each retrieved text chunk."""
+
+    max_token_for_global_context: int = 4000
+    """Maximum number of tokens allocated for relationship descriptions in global retrieval."""
+
+    max_token_for_local_context: int = 4000
+    """Maximum number of tokens allocated for entity descriptions in local retrieval."""
+
+    hl_keywords: List[str] = field(default_factory=list)
+    """List of high-level keywords to prioritize in retrieval."""
+
+    ll_keywords: List[str] = field(default_factory=list)
+    """List of low-level keywords to refine retrieval focus."""
+
+    conversation_history: List[dict[str, Any]] = field(default_factory=list)
+    """Stores past conversation history to maintain context.
+    Format: [{"role": "user/assistant", "content": "message"}].
+    """
+
+    history_turns: int = 3
+    """Number of complete conversation turns (user-assistant pairs) to consider in the response context."""
 
 @dataclass
 class StorageNameSpace: