如果您在colab上打开这个笔记本,您可能需要安装LlamaIndex 🦙。
%pip install llama-index-embeddings-huggingface
%pip install llama-index-vector-stores-awadb
!pip install llama-index
import logging
import sys
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))
from llama_index.core import (
SimpleDirectoryReader,
VectorStoreIndex,
StorageContext,
)
from IPython.display import Markdown, display
import openai
openai.api_key = ""
INFO:numexpr.utils:Note: NumExpr detected 12 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8. Note: NumExpr detected 12 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8. INFO:numexpr.utils:NumExpr defaulting to 8 threads. NumExpr defaulting to 8 threads.
!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'
# 加载文档
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.vector_stores.awadb import AwaDBVectorStore
embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
vector_store = AwaDBVectorStore()
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
documents, storage_context=storage_context, embed_model=embed_model
)
# 将日志级别设置为DEBUG,以获得更详细的输出
query_engine = index.as_query_engine()
response = query_engine.query("作者在成长过程中做了什么?")
display(Markdown(f"<b>{response}</b>"))
# 将日志级别设置为DEBUG,以获得更详细的输出
query_engine = index.as_query_engine()
response = query_engine.query(
"作者在Y Combinator结束后做了什么?"
)
display(Markdown(f"<b>{response}</b>"))