File size: 3,184 Bytes
8282222 6011708 8282222 a28a4f8 2826548 6011708 4359eb6 2826548 a28a4f8 2826548 8282222 6011708 95d2e5f 8282222 a28a4f8 2826548 8282222 a28a4f8 6011708 2826548 a28a4f8 8282222 2826548 6011708 a28a4f8 6011708 2826548 6011708 2826548 a28a4f8 2826548 6011708 a28a4f8 |
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 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
import os
from typing import List, Optional
from langchain.chains import ConversationChain, LLMChain
from langchain.prompts import PromptTemplate
from langchain.chains.base import Chain
from langchain.memory import ConversationSummaryBufferMemory
from app_modules.llm_inference import LLMInference
from app_modules.utils import CustomizedConversationSummaryBufferMemory
def get_llama_2_prompt_template():
B_INST, E_INST = "[INST]", "[/INST]"
B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n"
instruction = "Chat History:\n\n{history} \n\nUser: {input}"
system_prompt = "You are a helpful assistant, you always only answer for the assistant then you stop. Read the chat history to get context"
# system_prompt = """\
# You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information. \n\nDo not output any emotional expression. Read the chat history to get context.\
# """
SYSTEM_PROMPT = B_SYS + system_prompt + E_SYS
prompt_template = B_INST + SYSTEM_PROMPT + instruction + E_INST
return prompt_template
def get_orca_2_prompt_template():
system_message = "You are Orca, an AI language model created by Microsoft. You are a cautious assistant. You carefully follow instructions. You are helpful and harmless and you follow ethical guidelines and promote positive behavior."
user_message = "Chat History:\n\n{history} \n\nUser: {input}"
prompt_template = f"<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{user_message}<|im_end|>\n<|im_start|>assistant"
return prompt_template
class ChatChain(LLMInference):
def __init__(self, llm_loader):
super().__init__(llm_loader)
def create_chain(self) -> Chain:
template = (
get_llama_2_prompt_template()
if os.environ.get("USE_LLAMA_2_PROMPT_TEMPLATE") == "true"
else (
get_orca_2_prompt_template()
if os.environ.get("USE_ORCA_2_PROMPT_TEMPLATE") == "true"
else """You are a chatbot having a conversation with a human.
{history}
Human: {input}
Chatbot:"""
)
)
print(f"template: {template}")
prompt = PromptTemplate(input_variables=["history", "input"], template=template)
memory = CustomizedConversationSummaryBufferMemory(
llm=self.llm_loader.llm, max_token_limit=1024, return_messages=False
)
llm_chain = ConversationChain(
llm=self.llm_loader.llm,
prompt=prompt,
verbose=False,
memory=memory,
)
return llm_chain
def run_chain(self, chain, inputs, callbacks: Optional[List] = []):
return super().run_chain(chain, {"input": inputs["question"]}, callbacks)
|