Spaces:
Runtime error
Runtime error
File size: 1,903 Bytes
58d33f0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
from typing import Any, Dict, List
from pydantic import BaseModel
from langchain.memory.chat_memory import BaseChatMemory
from langchain.schema import BaseLanguageModel, BaseMessage, get_buffer_string
class ConversationTokenBufferMemory(BaseChatMemory, BaseModel):
"""Buffer for storing conversation memory."""
human_prefix: str = "Human"
ai_prefix: str = "AI"
llm: BaseLanguageModel
memory_key: str = "history"
max_token_limit: int = 2000
@property
def buffer(self) -> List[BaseMessage]:
"""String buffer of memory."""
return self.chat_memory.messages
@property
def memory_variables(self) -> List[str]:
"""Will always return list of memory variables.
:meta private:
"""
return [self.memory_key]
def load_memory_variables(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
"""Return history buffer."""
buffer: Any = self.buffer
if self.return_messages:
final_buffer: Any = buffer
else:
final_buffer = get_buffer_string(
buffer,
human_prefix=self.human_prefix,
ai_prefix=self.ai_prefix,
)
return {self.memory_key: final_buffer}
def save_context(self, inputs: Dict[str, Any], outputs: Dict[str, str]) -> None:
"""Save context from this conversation to buffer. Pruned."""
super().save_context(inputs, outputs)
# Prune buffer if it exceeds max token limit
buffer = self.chat_memory.messages
curr_buffer_length = self.llm.get_num_tokens_from_messages(buffer)
if curr_buffer_length > self.max_token_limit:
pruned_memory = []
while curr_buffer_length > self.max_token_limit:
pruned_memory.append(buffer.pop(0))
curr_buffer_length = self.llm.get_num_tokens_from_messages(buffer)
|