#!/usr/bin/env python
# coding: utf-8

# <a href="https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/docs/examples/vector_stores/DashvectorIndexDemo.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="在 Colab 中打开"/></a>
# 

# # DashVector 矢量存储库
# 

# 如果您在colab上打开这个笔记本，您可能需要安装LlamaIndex 🦙。
# 

# In[ ]:


get_ipython().run_line_magic('pip', 'install llama-index-vector-stores-dashvector')


# In[ ]:


get_ipython().system('pip install llama-index')


# In[ ]:


import logging
import sys
import os

logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))


# #### 创建一个DashVector集合
# 

# In[ ]:


import dashvector


# In[ ]:


api_key = os.environ["DASHVECTOR_API_KEY"]
client = dashvector.Client(api_key=api_key)


# In[ ]:


# 文本嵌入ada-002的维度client.create("llama-demo", dimension=1536)


# In[ ]:


dashvector_collection = client.get("quickstart")


# #### 下载数据
# 

# In[ ]:


get_ipython().system("mkdir -p 'data/paul_graham/'")
get_ipython().system("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，构建DashVectorStore和VectorStoreIndex
# 

# In[ ]:


from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.vector_stores.dashvector import DashVectorStore
from IPython.display import Markdown, display


# In[ ]:


# 加载文档documents = SimpleDirectoryReader("./data/paul_graham").load_data()


# In[ ]:


# 初始化，不带元数据过滤器from llama_index.core import StorageContextvector_store = DashVectorStore(dashvector_collection)storage_context = StorageContext.from_defaults(vector_store=vector_store)index = VectorStoreIndex.from_documents(    documents, storage_context=storage_context)


# ```python
# # 查询索引
# 
# 这个代码段演示了如何在Python中查询列表中的元素索引。
# 
# ```
# 

# In[ ]:


# 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？")


# In[ ]:


display(Markdown(f"<b>{response}</b>"))