NVIDIA Hands-on Lab——Building RAG Agents with LLMs

NVIDIA DLI RAG课程（Course Detail | NVIDIA )，并获得该课程证书。

1 07的ipynb文件中设定，使用这两个模型配置

embedder = NVIDIAEmbeddings(model="nvidia/nv-embed-v1", truncate="END")
# ChatNVIDIA.get_available_models()
instruct_llm = ChatNVIDIA(model="mistralai/mixtral-8x7b-instruct-v0.1")

大约会在Part3的 Task3出错，否则会早早出错。

08不用改

运行完 所有cell后，点击下面的绿色的 Link To Gradio Frontend 文字，跳转到我们服务启动的页面

35的ipynb文件脚本需要修改几处：

从07/08两个脚本中复制代码出来

从07 Part3复制如下

 
chat_prompt = ChatPromptTemplate.from_messages([("system",
    "You are a document chatbot. Help the user as they ask questions about documents."
    " User messaged just asked: {input}\n\n"
    " From this, we have retrieved the following potentially-useful info: "
    " Conversation History Retrieval:\n{history}\n\n"
    " Document Retrieval:\n{context}\n\n"
    " (Answer only from retrieval. Only cite sources that are used. Make your response conversational.)"
), ('user', '{input}')])
 
 
embedder = NVIDIAEmbeddings(model="nvidia/nv-embed-v1", truncate="END")

08 Part3 Task1 复制如下

from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings
from langchain_community.vectorstores import FAISS
 
docstore = FAISS.load_local("docstore_index", embedder, allow_dangerous_deserialization=True)
docs = list(docstore.docstore._dict.values())

再手写补充如下

 
add_routes(
    app,
    docstore.as_retriever(),
    path="/retriever",
)
 
 
add_routes(
    app,
    chat_prompt | llm,
    path="/generator",
)

然后将 08 中的问题复制粘贴到 到输入框中，运行即可。