Update README for QueryParam description

README.md

@@ -237,38 +237,65 @@ Use QueryParam to control the behavior your query:
 
 ```python
 class QueryParam:
-    mode: Literal["local", "global", "hybrid", "naive", "mix"] = "global"
+    """Configuration parameters for query execution in LightRAG."""
+
+    mode: Literal["local", "global", "hybrid", "naive", "mix", "bypass"] = "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. Mix mode combines knowledge graph and vector search:
-        - Uses both structured (KG) and unstructured (vector) information
-        - Provides comprehensive answers by analyzing relationships and context
-        - Supports image content through HTML img tags
-        - Allows control over retrieval depth via top_k parameter
+    - "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'."""
-    top_k: int = 60
+
+    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
+
+    max_token_for_text_unit: int = int(os.getenv("MAX_TOKEN_TEXT_CHUNK", "4000"))
     """Maximum number of tokens allowed for each retrieved text chunk."""
-    max_token_for_global_context: int = 4000
+
+    max_token_for_global_context: int = int(
+        os.getenv("MAX_TOKEN_RELATION_DESC", "4000")
+    )
     """Maximum number of tokens allocated for relationship descriptions in global retrieval."""
-    max_token_for_local_context: int = 4000
+
+    max_token_for_local_context: int = int(os.getenv("MAX_TOKEN_ENTITY_DESC", "4000"))
     """Maximum number of tokens allocated for entity descriptions in local retrieval."""
-    ids: list[str] | None = None # ONLY SUPPORTED FOR PG VECTOR DBs
-    """List of ids to filter the RAG."""
+
+    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, str]] = 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."""
+
+    ids: list[str] | None = None
+    """List of ids to filter the results."""
+
     model_func: Callable[..., object] | None = None
     """Optional override for the LLM model function to use for this specific query.
     If provided, this will be used instead of the global model function.
     This allows using different models for different query modes.
     """
-    ...
 ```
 
 > default value of Top_k can be change by environment  variables  TOP_K.