Python Coding

LLM Model API

LMStudio

from langchain.llms import OpenAI

#set llm for langchain using model from lmstudio
llm = OpenAI(
       openai_api_base='http://localhost:1234/v1',
       openai_api_key='NULL'
       )

import streamlit as st
from openai import OpenAI

# Set up the Streamlit App
st.title("ChatGPT Clone using Llama-3 🦙")
st.caption("Chat with locally hosted Llama-3 using the LM Studio 💯")

# Point to the local server setup using LM Studio
client = OpenAI(base_url="http://localhost:1234/v1", api_key="lm-studio")

# Initialize the chat history
if "messages" not in st.session_state:
    st.session_state.messages = []

# Display the chat history
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

# Accept user input
if prompt := st.chat_input("What is up?"):
    # Add user message to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})
    # Display user message in chat message container
    with st.chat_message("user"):
        st.markdown(prompt)
    # Generate response
    response = client.chat.completions.create(
        model="lmstudio-community/Meta-Llama-3-8B-Instruct-GGUF",
        messages=st.session_state.messages, temperature=0.7
    )
    # Add assistant response to chat history
    st.session_state.messages.append({"role": "assistant", "content": response.choices[0].message.content})
    # Display assistant response in chat message container
    with st.chat_message("assistant"):
        st.markdown(response.choices[0].message.content)

GPT

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-4o",
    temperature=0,
    max_tokens=None,
    timeout=None,
    max_retries=2,
    # api_key="...",
    # base_url="...",
    # organization="...",
    # other params...
)

Ollama

from langchain_community.llms import Ollama

llm = Ollama(model="llama2:13b")
llm.invoke("The first man on the moon was ... think step by step")

Chunking/Splitting

中文句子切割

# Unicode 編碼
#   \u3002 全形句號
#   \uff0c 全形逗號
# Get Unicode for specific character
# >>> '，'.encode('unicode-escape') # for py3
# >>> list(u'，') # for py2

import re
text = "這是中文句子。第一段，第二段，第三段。"
chunks = re.split('[\u3002\uff0c]', text)
#print("\n\n".join([chunk for chunk in chunks]))
for chunk in chunks:
    print("---" * 10)
    print(chunk)

英文句子切割

# \s+ 單或多個空白
chunks = re.split(r'(?<=[.?!])\s+', text)