# 安装所需依赖
pip install -qU  clarifai langchain-community

# 请登录并从 https://clarifai.com/settings/security 获取您的 API 密钥
from getpass import getpass

CLARIFAI_PAT = getpass()

 ········

# 导入所需模块
from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import Clarifai
from langchain_text_splitters import CharacterTextSplitter

USER_ID = "USERNAME_ID"
APP_ID = "APPLICATION_ID"
NUMBER_OF_DOCS = 2

texts = [
    "I really enjoy spending time with you",
    "I hate spending time with my dog",
    "I want to go for a run",
    "I went to the movies yesterday",
    "I love playing soccer with my friends",
]

metadatas = [
    {"id": i, "text": text, "source": "book 1", "category": ["books", "modern"]}
    for i, text in enumerate(texts)
]

idlist = ["text1", "text2", "text3", "text4", "text5"]
metadatas = [
    {"id": idlist[i], "text": text, "source": "book 1", "category": ["books", "modern"]}
    for i, text in enumerate(texts)
]

# 可以使用 pat 参数初始化 clarifai 向量存储！
clarifai_vector_db = Clarifai(
    user_id=USER_ID,
    app_id=APP_ID,
    number_of_docs=NUMBER_OF_DOCS,
)

# 使用元数据和自定义输入 ID 上传。
response = clarifai_vector_db.add_texts(texts=texts, ids=idlist, metadatas=metadatas)

# 不带元数据上传（不推荐）- 因为这样将无法根据元数据执行搜索操作。
# 自定义 input_id（可选）
response = clarifai_vector_db.add_texts(texts=texts)

clarifai_vector_db = Clarifai.from_texts(
    user_id=USER_ID,
    app_id=APP_ID,
    texts=texts,
    metadatas=metadatas,
)

docs = clarifai_vector_db.similarity_search("I would like to see you")
docs

[Document(page_content='I really enjoy spending time with you', metadata={'text': 'I really enjoy spending time with you', 'id': 'text1', 'source': 'book 1', 'category': ['books', 'modern']})]

# 在应用中，您可以利用元数据过滤器进行强大的筛选。
# 以下示例将相似度查询限制在 "source" 键值为 "book 1" 的文本中
book1_similar_docs = clarifai_vector_db.similarity_search(
    "I would love to see you", filter={"source": "book 1"}
)

# 您也可以在输入的元数据中使用列表，然后选择匹配列表中某一项的内容。这对于如下所示的分类场景非常有用：
book_category_similar_docs = clarifai_vector_db.similarity_search(
    "I would love to see you", filter={"category": ["books"]}
)

loader = TextLoader("your_local_file_path.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

USER_ID = "USERNAME_ID"
APP_ID = "APPLICATION_ID"
NUMBER_OF_DOCS = 4

clarifai_vector_db = Clarifai.from_documents(
    user_id=USER_ID,
    app_id=APP_ID,
    documents=docs,
    number_of_docs=NUMBER_OF_DOCS,
)

docs = clarifai_vector_db.similarity_search("Texts related to population")
docs

USER_ID = "USERNAME_ID"
APP_ID = "APPLICATION_ID"
NUMBER_OF_DOCS = 4

clarifai_vector_db = Clarifai(
    user_id=USER_ID,
    app_id=APP_ID,
    number_of_docs=NUMBER_OF_DOCS,
)

docs = clarifai_vector_db.similarity_search(
    "Texts related to ammuniction and president wilson"
)

docs[0].page_content

"President Wilson, generally acclaimed as the leader of the world's democracies,\nphrased for civilization the arguments against autocracy in the great peace conference\nafter the war. The President headed the American delegation to that conclave of world\nre-construction. With him as delegates to the conference were Robert Lansing, Secretary\nof State; Henry White, former Ambassador to France and Italy; Edward M. House and\nGeneral Tasker H. Bliss.\nRepresenting American Labor at the International Labor conference held in Paris\nsimultaneously with the Peace Conference were Samuel Gompers, president of the\nAmerican Federation of Labor; William Green, secretary-treasurer of the United Mine\nWorkers of America; John R. Alpine, president of the Plumbers' Union; James Duncan,\npresident of the International Association of Granite Cutters; Frank Duffy, president of\nthe United Brotherhood of Carpenters and Joiners, and Frank Morrison, secretary of the\nAmerican Federation of Labor.\nEstimating the share of each Allied nation in the great victory, mankind will\nconclude that the heaviest cost in proportion to prewar population and treasure was paid\nby the nations that first felt the shock of war, Belgium, Serbia, Poland and France. All\nfour were the battle-grounds of huge armies, oscillating in a bloody frenzy over once\nfertile fields and once prosperous towns.\nBelgium, with a population of 8,000,000, had a casualty list of more than 350,000;\nFrance, with its casualties of 4,000,000 out of a population (including its colonies) of\n90,000,000, is really the martyr nation of the world. Her gallant poilus showed the world\nhow cheerfully men may die in defense of home and liberty. Huge Russia, including\nhapless Poland, had a casualty list of 7,000,000 out of its entire population of\n180,000,000. The United States out of a population of 110,000,000 had a casualty list of\n236,117 for nineteen months of war; of these 53,169 were killed or died of disease;\n179,625 were wounded; and 3,323 prisoners or missing."