书生大模型实战营第三期_LlamaIndex RAG 实践（81班1101作业）

基础任务 (完成此任务即完成闯关)

• 任务要求：基于 LlamaIndex 构建自己的 RAG 知识库，寻找一个问题 A 在使用 LlamaIndex 之前InternLM2-Chat-1.8B模型不会回答，借助 LlamaIndex 后 InternLM2-Chat-1.8B 模型具备回答 A 的能力，截图保存。

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings

from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.llms.huggingface import HuggingFaceLLM

from transformers import BitsAndBytesConfig
import torch

quantization_config = BitsAndBytesConfig(
            load_in_4bit=True,
            bnb_4bit_compute_dtype=torch.float16,
            bnb_4bit_quant_type="nf4",
            bnb_4bit_use_double_quant=True,
        )

embed_model = HuggingFaceEmbedding(
    model_name="/root/model/sentence-transformer"
)

Settings.embed_model = embed_model

llm = HuggingFaceLLM(
    model_name="/root/model/internlm2-chat-1_8b",
    tokenizer_name="/root/model/internlm2-chat-1_8b",
    model_kwargs={"trust_remote_code":True,"quantization_config": quantization_config},
    tokenizer_kwargs={"trust_remote_code":True}
)
Settings.llm = llm

documents = SimpleDirectoryReader("/root/llamaindex_demo/data").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
response = query_engine.query("xtuner是什么?")

print(response)

无RAG返回截图

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings

from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.llms.huggingface import HuggingFaceLLM

from transformers import BitsAndBytesConfig
import torch

quantization_config = BitsAndBytesConfig(
            load_in_4bit=True,
            bnb_4bit_compute_dtype=torch.float16,
            bnb_4bit_quant_type="nf4",
            bnb_4bit_use_double_quant=True,
        )

embed_model = HuggingFaceEmbedding(
    model_name="/root/model/sentence-transformer"
)

Settings.embed_model = embed_model

llm = HuggingFaceLLM(
    model_name="/root/model/internlm2-chat-1_8b",
    tokenizer_name="/root/model/internlm2-chat-1_8b",
    model_kwargs={"trust_remote_code":True,"quantization_config": quantization_config},
    tokenizer_kwargs={"trust_remote_code":True}
)
Settings.llm = llm

documents = SimpleDirectoryReader("/root/llamaindex_demo/data").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
response = query_engine.query("xtuner是什么?")

print(response)

RAG返回截图