Build LLM Application Step by Step

pyenv virtualenv llm
pyenv activate llm
pip install -r requirements.txt

prompt_template = '''You are a translator and your task is to translate l10n file to different languages.
The l10n file is provided in TOML format. The file contains {{ KEY }} for variables and use
`one` for singular and `other` for plural.

The TOML file is quoted in triple backtick. Please translate the content to {lang}
and keep the original content structure, also remove triple backtick in output:

```toml
{en_file_content}
```
'''

# flake8: noqa
from langchain_core.prompts.prompt import PromptTemplate

EXAMPLES = [
    """Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
Thought: I need to search Colorado orogeny, find the area that the eastern sector of the Colorado orogeny extends into, then find the elevation range of the area.
Action: Search[Colorado orogeny]
Observation: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas.
Thought: It does not mention the eastern sector. So I need to look up eastern sector.
Action: Lookup[eastern sector]
Observation: (Result 1 / 1) The eastern sector extends into the High Plains and is called the Central Plains orogeny.
Thought: The eastern sector of Colorado orogeny extends into the High Plains. So I need to search High Plains and find its elevation range.
Action: Search[High Plains]
Observation: High Plains refers to one of two distinct land regions
Thought: I need to instead search High Plains (United States).
Action: Search[High Plains (United States)]
Observation: The High Plains are a subregion of the Great Plains. From east to west, the High Plains rise in elevation from around 1,800 to 7,000 ft (550 to 2,130 m).[3]
Thought: High Plains rise in elevation from around 1,800 to 7,000 ft, so the answer is 1,800 to 7,000 ft.
Action: Finish[1,800 to 7,000 ft]""",
    ...
]
SUFFIX = """\nQuestion: {input}
{agent_scratchpad}"""

WIKI_PROMPT = PromptTemplate.from_examples(
    EXAMPLES, SUFFIX, ["input", "agent_scratchpad"]
)

for m in genai.list_models():
  if 'embedContent' in m.supported_generation_methods:
    print(m.name)

# output:
# models/embedding-001
# models/text-embedding-004

title = "The next generation of AI for developers and Google Workspace"
sample_text = ("Title: The next generation of AI for developers and Google Workspace"
    "\n"
    "Full article:\n"
    "\n"
    "Gemini API & Google AI Studio: An approachable way to explore and prototype with generative AI applications")

model = 'models/text-embedding-004'
embedding = genai.embed_content(model=model,
                                content=sample_text,
                                task_type="retrieval_document",
                                title=title)

print(embedding)

{'embedding': [-0.0021609126, -0.003164448, -0.060120765, ...]}

pattern = re.compile(r'[^\u4e00-\u9fff](\n)[^\u4e00-\u9fff]', re.DOTALL)

import re
pattern = re.compile(r'[^\u4e00-\u9fff](\n)[^\u4e00-\u9fff]', re.DOTALL)

page_content = '''前言
“周志华老师的《机器学习》
（西瓜书）是机器学习领域的经典入门课程之一，周老师为了使尽可能多的读
者通过西瓜书对机器学习有所了解, 所以在书中对部分公式的推导细节没有详述，但是这对那些想深究公式推
导细节的读者来说可能“不太友好”
，本书旨在对西瓜书里比较难理解的公式加以解析，以及对部分公式补充
具体的推导细节。
”'''
print(re.sub(pattern, lambda match: match.group(0).replace('\n', ''), page_content))

import os
file_paths = []
folder_path = './llm-universe/data_base/knowledge_db'
for root, dirs, files in os.walk(folder_path):
    for file in files:
        file_path = os.path.join(root, file)
        file_paths.append(file_path)

from langchain.document_loaders.pdf import PyMuPDFLoader
from langchain.document_loaders.markdown import UnstructuredMarkdownLoader

# 遍历文件路径并把实例化的loader存放在loaders里
loaders = []

for file_path in file_paths:
    _, file_type = os.path.splitext(file_path)  # os.path.splitext是更pythonic的写法
    if file_type == '.pdf':
        loaders.append(PyMuPDFLoader(file_path))
    elif file_type == '.md':
        loaders.append(UnstructuredMarkdownLoader(file_path))

!pip install --quiet langchain-google-genai
from langchain.vectorstores.chroma import Chroma
from langchain_google_genai import GoogleGenerativeAIEmbeddings
gemini_embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")

vectordb = Chroma.from_documents(
                     documents=split_docs[:20],      # Data
                     embedding=gemini_embeddings,    # Embedding model
                     persist_directory="./chroma_db" # Directory to save data
                     )

vectordb.persist()

question="什么是大语言模型"
sim_docs = vectordb.similarity_search(question,k=3)
print(f"检索到的内容数：{len(sim_docs)}")
for i, sim_doc in enumerate(sim_docs):
    print(f"检索到的第{i}个内容: \n{sim_doc.page_content[:200]}", end="\n--------------\n")

from langchain_google_genai import ChatGoogleGenerativeAI
llm = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.1, top_p=0.85)
llm.invoke("Who are you?")

from langchain.prompts.chat import ChatPromptTemplate

template = "你是一个翻译助手，可以帮助我将 {input_language} 翻译成 {output_language}."
human_template = "{text}"

chat_prompt = ChatPromptTemplate.from_messages([
    ("system", template),
    ("human", human_template),
])

text = "我带着比身体重的行李，\
游入尼罗河底，\
经过几道闪电 看到一堆光圈，\
不确定是不是这里。\
"
messages  = chat_prompt.format_messages(input_language="中文", output_language="英文", text=text)
print(messages)
llm.invoke(messages)

from langchain_core.prompts import PromptTemplate
from langchain_core.output_parsers import StrOutputParser

template = """你是一个翻译助手，可以帮助我将 {input_language} 翻译成 {output_language}.
{text}"""

prompt = PromptTemplate.from_template(template)
chain = prompt | llm | StrOutputParser()
chain.invoke({"input_language":"中文", "output_language":"英文","text": text})

llm = ChatGoogleGenerativeAI(model="gemini-1.5-pro-latest",
                 temperature=0.1, top_p=0.85)

qa = ConversationalRetrievalChain.from_llm(
    llm,
    retriever=retriever,
    memory=memory
)