c3c25db48c
- Use cases related to LLM call: https://cinnamon-ai.atlassian.net/browse/AUR-388?focusedCommentId=34873 - Sample usages: `test_llms_chat_models.py` and `test_llms_completion_models.py`: ```python from kotaemon.llms.chats.openai import AzureChatOpenAI model = AzureChatOpenAI( openai_api_base="https://test.openai.azure.com/", openai_api_key="some-key", openai_api_version="2023-03-15-preview", deployment_name="gpt35turbo", temperature=0, request_timeout=60, ) output = model("hello world") ``` For the LLM-call component, I decide to wrap around Langchain's LLM models and Langchain's Chat models. And set the interface as follow: - Completion LLM component: ```python class CompletionLLM: def run_raw(self, text: str) -> LLMInterface: # Run text completion: str in -> LLMInterface out def run_batch_raw(self, text: list[str]) -> list[LLMInterface]: # Run text completion in batch: list[str] in -> list[LLMInterface] out # run_document and run_batch_document just reuse run_raw and run_batch_raw, due to unclear use case ``` - Chat LLM component: ```python class ChatLLM: def run_raw(self, text: str) -> LLMInterface: # Run chat completion (no chat history): str in -> LLMInterface out def run_batch_raw(self, text: list[str]) -> list[LLMInterface]: # Run chat completion in batch mode (no chat history): list[str] in -> list[LLMInterface] out def run_document(self, text: list[BaseMessage]) -> LLMInterface: # Run chat completion (with chat history): list[langchain's BaseMessage] in -> LLMInterface out def run_batch_document(self, text: list[list[BaseMessage]]) -> list[LLMInterface]: # Run chat completion in batch mode (with chat history): list[list[langchain's BaseMessage]] in -> list[LLMInterface] out ``` - The LLMInterface is as follow: ```python @dataclass class LLMInterface: text: list[str] completion_tokens: int = -1 total_tokens: int = -1 prompt_tokens: int = -1 logits: list[list[float]] = field(default_factory=list) ```
86 lines
2.6 KiB
Python
86 lines
2.6 KiB
Python
from typing import Type, TypeVar
|
|
|
|
from theflow.base import Param
|
|
from langchain.schema.language_model import BaseLanguageModel
|
|
|
|
from langchain.schema.messages import (
|
|
BaseMessage,
|
|
HumanMessage,
|
|
)
|
|
|
|
from ...components import BaseComponent
|
|
from ..base import LLMInterface
|
|
|
|
|
|
Message = TypeVar("Message", bound=BaseMessage)
|
|
|
|
|
|
class ChatLLM(BaseComponent):
|
|
...
|
|
|
|
|
|
class LangchainChatLLM(ChatLLM):
|
|
_lc_class: Type[BaseLanguageModel]
|
|
|
|
def __init__(self, **params):
|
|
if self._lc_class is None:
|
|
raise AttributeError(
|
|
"Should set _lc_class attribute to the LLM class from Langchain "
|
|
"if using LLM from Langchain"
|
|
)
|
|
|
|
self._kwargs: dict = {}
|
|
for param in list(params.keys()):
|
|
if param in self._lc_class.__fields__:
|
|
self._kwargs[param] = params.pop(param)
|
|
super().__init__(**params)
|
|
|
|
@Param.decorate()
|
|
def agent(self):
|
|
return self._lc_class(**self._kwargs)
|
|
|
|
def run_raw(self, text: str) -> LLMInterface:
|
|
message = HumanMessage(content=text)
|
|
return self.run_document([message])
|
|
|
|
def run_batch_raw(self, text: list[str]) -> list[LLMInterface]:
|
|
inputs = [[HumanMessage(content=each)] for each in text]
|
|
return self.run_batch_document(inputs)
|
|
|
|
def run_document(self, text: list[Message]) -> LLMInterface:
|
|
pred = self.agent.generate([text])
|
|
return LLMInterface(
|
|
text=[each.text for each in pred.generations[0]],
|
|
completion_tokens=pred.llm_output["token_usage"]["completion_tokens"],
|
|
total_tokens=pred.llm_output["token_usage"]["total_tokens"],
|
|
prompt_tokens=pred.llm_output["token_usage"]["prompt_tokens"],
|
|
logits=[],
|
|
)
|
|
|
|
def run_batch_document(self, text: list[list[Message]]) -> list[LLMInterface]:
|
|
outputs = []
|
|
for each_text in text:
|
|
outputs.append(self.run_document(each_text))
|
|
return outputs
|
|
|
|
def is_document(self, text) -> bool:
|
|
if isinstance(text, str):
|
|
return False
|
|
elif isinstance(text, list) and isinstance(text[0], str):
|
|
return False
|
|
return True
|
|
|
|
def is_batch(self, text) -> bool:
|
|
if isinstance(text, str):
|
|
return False
|
|
elif isinstance(text, list):
|
|
if isinstance(text[0], BaseMessage):
|
|
return False
|
|
return True
|
|
|
|
def __setattr__(self, name, value):
|
|
if name in self._lc_class.__fields__:
|
|
setattr(self.agent, name, value)
|
|
else:
|
|
super().__setattr__(name, value)
|