langroid 0.1.85__py3-none-any.whl → 0.1.219__py3-none-any.whl

langroid/agent/chat_document.py

@@ -1,8 +1,9 @@
 import json
-from typing import List, Optional, Type
+from typing import List, Optional, Union
 
 from pydantic import BaseModel, Extra
 
+from langroid.agent.tool_message import ToolMessage
 from langroid.language_models.base import (
     LLMFunctionCall,
     LLMMessage,
@@ -12,7 +13,7 @@ from langroid.language_models.base import (
 )
 from langroid.mytypes import DocMetaData, Document, Entity
 from langroid.parsing.agent_chats import parse_message
-from langroid.parsing.json import extract_top_level_json, top_level_json_field
+from langroid.parsing.parse_json import extract_top_level_json, top_level_json_field
 from langroid.utils.output.printing import shorten_text
 
 
@@ -25,6 +26,7 @@ class ChatDocAttachment(BaseModel):
 class ChatDocMetaData(DocMetaData):
     parent: Optional["ChatDocument"] = None
     sender: Entity
+    tool_ids: List[str] = []  # stack of tool_ids; used by OpenAIAssistant
     # when result returns to parent, pretend message is from this entity
     parent_responder: None | Entity = None
     block: None | Entity = None
@@ -52,6 +54,7 @@ class ChatDocLoggerFields(BaseModel):
 
 class ChatDocument(Document):
     function_call: Optional[LLMFunctionCall] = None
+    tool_messages: List[ToolMessage] = []
     metadata: ChatDocMetaData
     attachment: None | ChatDocAttachment = None
 
@@ -81,7 +84,7 @@ class ChatDocument(Document):
             json_data = json.loads(j)
             tool = json_data.get("request")
             if tool is not None:
-                tools.append(tool)
+                tools.append(str(tool))
         return tools
 
     def log_fields(self) -> ChatDocLoggerFields:
@@ -102,6 +105,8 @@ class ChatDocument(Document):
         content = self.content
         sender_entity = self.metadata.sender
         sender_name = self.metadata.sender_name
+        if tool_type == "FUNC":
+            content += str(self.function_call)
         return ChatDocLoggerFields(
             sender_entity=sender_entity,
             sender_name=sender_name,
@@ -118,12 +123,30 @@ class ChatDocument(Document):
         field_values = fields.dict().values()
         return "\t".join(str(v) for v in field_values)
 
+    def pop_tool_ids(self) -> None:
+        """
+        Pop the last tool_id from the stack of tool_ids.
+        """
+        if len(self.metadata.tool_ids) > 0:
+            self.metadata.tool_ids.pop()
+
     @staticmethod
     def from_LLMResponse(
         response: LLMResponse,
         displayed: bool = False,
     ) -> "ChatDocument":
+        """
+        Convert LLMResponse to ChatDocument.
+        Args:
+            response (LLMResponse): LLMResponse to convert.
+            displayed (bool): Whether this response was displayed to the user.
+        Returns:
+            ChatDocument: ChatDocument representation of this LLMResponse.
+        """
         recipient, message = response.get_recipient_and_message()
+        message = message.strip()
+        if message in ["''", '""']:
+            message = ""
         return ChatDocument(
             content=message,
             function_call=response.function_call,
@@ -155,7 +178,7 @@ class ChatDocument(Document):
         )
 
     @staticmethod
-    def to_LLMMessage(message: str | Type["ChatDocument"]) -> LLMMessage:
+    def to_LLMMessage(message: Union[str, "ChatDocument"]) -> LLMMessage:
         """
         Convert to LLMMessage for use with LLM.
 
@@ -168,10 +191,23 @@ class ChatDocument(Document):
         sender_name = None
         sender_role = Role.USER
         fun_call = None
+        tool_id = ""
         if isinstance(message, ChatDocument):
             content = message.content
             fun_call = message.function_call
+            if message.metadata.sender == Entity.USER and fun_call is not None:
+                # This may happen when a (parent agent's) LLM generates a
+                # a Function-call, and it ends up being sent to the current task's
+                # LLM (possibly because the function-call is mis-named or has other
+                # issues and couldn't be handled by handler methods).
+                # But a function-call can only be generated by an entity with
+                # Role.ASSISTANT, so we instead put the content of the function-call
+                # in the content of the message.
+                content += " " + str(fun_call)
+                fun_call = None
             sender_name = message.metadata.sender_name
+            tool_ids = message.metadata.tool_ids
+            tool_id = tool_ids[-1] if len(tool_ids) > 0 else ""
             if message.metadata.sender == Entity.SYSTEM:
                 sender_role = Role.SYSTEM
             if (
@@ -188,6 +224,7 @@ class ChatDocument(Document):
 
         return LLMMessage(
             role=sender_role,
+            tool_id=tool_id,
             content=content,
             function_call=fun_call,
             name=sender_name,