defset_sidebar():
"""Setup sidebar for API keys and configuration."""
withst.sidebar:
st.subheader("API Configuration")
qdrant_host = st.text_input("Enter your Qdrant Host URL:",type="password")
qdrant_api_key = st.text_input("Enter your Qdrant API key:",type="password")
gemini_api_key = st.text_input("Enter your Gemini API key:",type="password")
ifst.button("Done"):
ifqdrant_hostandqdrant_api_keyandgemini_api_key:
st.session_state.qdrant_host = qdrant_host
st.session_state.qdrant_api_key = qdrant_api_key
st.session_state.gemini_api_key = gemini_api_key
st.success("API keys saved!")
else:
st.warning("Please fill all API fields")grade_documents 用 Gemini 对「用户提问」和「搜索结果/资料」进行相似度判断，LLM只能回答 yes / no，若为 yes 则走 generate 把问题和资料一起给LLM写一段简洁准确的回复输出给用户，若为 no 则重新搜索，重新检索前LLM会把用户原问题改写成更贴切、更好搜索的内容。
# LLM
model = ChatGoogleGenerativeAI(api_key=st.session_state.gemini_api_key, temperature=0, model="gemini-2.0-flash", streaming=True)
# LLM with tool and validation
llm_with_tool = model.with_structured_output(grade)
# Prompt
prompt = PromptTemplate(
template="""You are a grader assessing relevance of a retrieved document to a user question. \n
Here is the retrieved document: \n\n {context} \n\n
Here is the user question: {question} \n
If the document contains keyword(s) or semantic meaning related to the user question, grade it as relevant. \n
Give a binary score 'yes' or 'no' score to indicate whether the document is relevant to the question.""",
input_variables=["context","question"],
)
# Chain
chain = prompt | llm_with_tool
messages = state["messages"]
last_message = messages[-1]
question = messages[0].content
docs = last_message.content
scored_result = chain.invoke({"question": question,"context": docs})
score = scored_result.binary_score
ifscore =="yes":
print("---DECISION: DOCS RELEVANT---")
return"generate"
else:
print("---DECISION: DOCS NOT RELEVANT---")
print(score)
return"rewrite"在 main 函数里，会把上述所有流程走一遍，首先check Qdrant地址和key & Gemini api key，将博客内容全文抓取下来，用 embedding_model 变为向量，切成 chunk 并配好编号 UUID，连接 Qdrant 存入 chunk 内容，成功的内容显示绿色，失败的显示红色。当用户Query输入后，LLM 判断数据库中是否有相似内容，若有则将问题和内容合并生成简洁回复显示在网页上，若无则改写问题重新检索，最多改写一次，查不到就结束，不会无限循环，节省 token 和时间消耗。
defmain():
set_sidebar()
# Check if API keys are set
ifnotall([st.session_state.qdrant_host,
st.session_state.qdrant_api_key,
st.session_state.gemini_api_key]):
st.warning("Please configure your API keys in the sidebar first")
return
# Initialize components
embedding_model, client, db = initialize_components()
ifnotall([embedding_model, client, db]):
return
# Initialize retriever and tools
retriever = db.as_retriever(search_type="similarity", search_kwargs={"k":5})
retriever_tool = create_retriever_tool(
retriever,
"retrieve_blog_posts",
"Search and return information about blog posts on LLMs, LLM agents, prompt engineering, and adversarial attacks on LLMs.",
)
tools = [retriever_tool]
# URL input section
url = st.text_input(
":link: Paste the blog link:",
placeholder="e.g., https://lilianweng.github.io/posts/2023-06-23-agent/"
)
ifst.button("Enter URL"):
ifurl:
withst.spinner("Processing documents..."):
ifadd_documents_to_qdrant(url, db):
st.success("Documents added successfully!")
else:
st.error("Failed to add documents")
else:
st.warning("Please enter a URL")
# Query section
graph = get_graph(retriever_tool)
query = st.text_area(
":bulb: Enter your query about the blog post:",
placeholder="e.g., What does Lilian Weng say about the types of agent memory?"
)
ifst.button("Submit Query"):
ifnotquery:
st.warning("Please enter a query")
return
inputs = {"messages": [HumanMessage(content=query)]}
withst.spinner("Generating response..."):
try:
response = generate_message(graph, inputs)
st.write(response)
exceptExceptionase:
st.error(f"Error generating response:{str(e)}")
st.markdown("---")
st.write("Built with :blue-background[LangChain] | :blue-background[LangGraph] by [Charan](https://www.linkedin.com/in/codewithcharan/)")
if__name__ =="__main__":
main()| 欢迎光临 链载Ai (https://www.lianzai.com/) | Powered by Discuz! X3.5 |