跳到内容

Metaphor

MetaphorToolSpec #

基类：BaseToolSpec

Metaphor 工具规范。

源代码位于 llama-index-integrations/tools/llama-index-tools-metaphor/llama_index/tools/metaphor/base.py 
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
class MetaphorToolSpec(BaseToolSpec):
    """Metaphor tool spec."""

    spec_functions = [
        "search",
        "retrieve_documents",
        "search_and_retrieve_documents",
        "find_similar",
        "current_date",
    ]

    def __init__(self, api_key: str, verbose: bool = True) -> None:
        """Initialize with parameters."""
        from metaphor_python import Metaphor

        self.client = Metaphor(api_key=api_key, user_agent="llama-index")
        self._verbose = verbose

    def search(
        self,
        query: str,
        num_results: Optional[int] = 10,
        include_domains: Optional[List[str]] = None,
        exclude_domains: Optional[List[str]] = None,
        start_published_date: Optional[str] = None,
        end_published_date: Optional[str] = None,
    ) -> str:
        """
        Metaphor allows you to use a natural language query to search the internet.

        Args:
            query (str): A natural language query phrased as an answer for what the link provides, ie: "This is the latest news about space:"
            num_results (Optional[int]): Number of results to return. Defaults to 10.
            include_domains (Optional[List(str)]): A list of top level domains like ["wsj.com"] to limit the search to specific sites.
            exclude_domains (Optional[List(str)]): Top level domains to exclude.
            start_published_date (Optional[str]): A date string like "2020-06-15". Get the date from `current_date`
            end_published_date (Optional[str]): End date string

        """
        response = self.client.search(
            query,
            num_results=num_results,
            include_domains=include_domains,
            exclude_domains=exclude_domains,
            start_published_date=start_published_date,
            end_published_date=end_published_date,
            use_autoprompt=True,
        )
        if self._verbose:
            print(f"[Metaphor Tool] Autoprompt: {response.autoprompt_string}")
        return [
            {"title": result.title, "url": result.url, "id": result.id}
            for result in response.results
        ]

    def retrieve_documents(self, ids: List[str]) -> List[Document]:
        """
        Retrieve a list of document summaries returned by `metaphor_search`, using the ID field.

        Args:
            ids (List(str)): the ids of the documents to retrieve

        """
        response = self.client.get_contents(ids)
        return [Document(text=con.extract) for con in response.contents]

    def find_similar(
        self,
        url: str,
        num_results: Optional[int] = 3,
        start_published_date: Optional[str] = None,
        end_published_date: Optional[str] = None,
    ) -> str:
        """
        Retrieve a list of similar documents to a given url.

        Args:
            url (str): The web page to find similar results of
            num_results (Optional[int]): Number of results to return. Default 3.
            start_published_date (Optional[str]): A date string like "2020-06-15"
            end_published_date (Optional[str]): End date string

        """
        response = self.client.find_similar(
            url,
            num_results=num_results,
            start_published_date=start_published_date,
            end_published_date=end_published_date,
        )
        return [
            {"title": result.title, "url": result.url, "id": result.id}
            for result in response.results
        ]

    def search_and_retrieve_documents(
        self,
        query: str,
        num_results: Optional[int] = 10,
        include_domains: Optional[List[str]] = None,
        exclude_domains: Optional[List[str]] = None,
        start_published_date: Optional[str] = None,
        end_published_date: Optional[str] = None,
    ) -> str:
        """
        Combines the functionality of `search` and `retrieve_documents`.

        Args:
            query (str): the natural language query
            num_results (Optional[int]): Number of results. Defaults to 10.
            include_domains (Optional[List(str)]): A list of top level domains to search, like ["wsj.com"]
            exclude_domains (Optional[List(str)]): Top level domains to exclude.
            start_published_date (Optional[str]): A date string like "2020-06-15".
            end_published_date (Optional[str]): End date string

        """
        response = self.client.search(
            query,
            num_results=num_results,
            include_domains=include_domains,
            exclude_domains=exclude_domains,
            start_published_date=start_published_date,
            end_published_date=end_published_date,
            use_autoprompt=True,
        )
        if self._verbose:
            print(f"[Metaphor Tool] Autoprompt: {response.autoprompt_string}")
        ids = [result.id for result in response.results]
        documents = self.client.get_contents(ids)
        return [Document(text=document.extract) for document in documents.contents]

    def current_date(self):
        """
        A function to return todays date.
        Call this before any other functions that take timestamps as an argument.
        """
        return datetime.date.today()

search #

search(query: str, num_results: Optional[int] = 10, include_domains: Optional[List[str]] = None, exclude_domains: Optional[List[str]] = None, start_published_date: Optional[str] = None, end_published_date: Optional[str] = None) -> str

Metaphor 允许您使用自然语言查询来搜索互联网。

参数

名称 类型 描述 默认值
query str

自然语言查询，表达为链接提供内容的答案，例如：“这是关于太空的最新消息：”

 必需的
num_results Optional[int]

返回结果的数量。默认为 10。

 10
include_domains Optional[List(str)]

顶级域名列表，例如 ["wsj.com"]，用于将搜索限制到特定网站。

 无
exclude_domains Optional[List(str)]

要排除的顶级域名。

 无
start_published_date Optional[str]

日期字符串，例如 “2020-06-15”。从 current_date 获取日期

 无
end_published_date Optional[str]

结束日期字符串

 无
源代码位于 llama-index-integrations/tools/llama-index-tools-metaphor/llama_index/tools/metaphor/base.py 
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
def search(
    self,
    query: str,
    num_results: Optional[int] = 10,
    include_domains: Optional[List[str]] = None,
    exclude_domains: Optional[List[str]] = None,
    start_published_date: Optional[str] = None,
    end_published_date: Optional[str] = None,
) -> str:
    """
    Metaphor allows you to use a natural language query to search the internet.

    Args:
        query (str): A natural language query phrased as an answer for what the link provides, ie: "This is the latest news about space:"
        num_results (Optional[int]): Number of results to return. Defaults to 10.
        include_domains (Optional[List(str)]): A list of top level domains like ["wsj.com"] to limit the search to specific sites.
        exclude_domains (Optional[List(str)]): Top level domains to exclude.
        start_published_date (Optional[str]): A date string like "2020-06-15". Get the date from `current_date`
        end_published_date (Optional[str]): End date string

    """
    response = self.client.search(
        query,
        num_results=num_results,
        include_domains=include_domains,
        exclude_domains=exclude_domains,
        start_published_date=start_published_date,
        end_published_date=end_published_date,
        use_autoprompt=True,
    )
    if self._verbose:
        print(f"[Metaphor Tool] Autoprompt: {response.autoprompt_string}")
    return [
        {"title": result.title, "url": result.url, "id": result.id}
        for result in response.results
    ]

retrieve_documents #

retrieve_documents(ids: List[str]) -> List[Document]

使用 ID 字段，检索 metaphor_search 返回的文档摘要列表。

参数

名称 类型 描述 默认值
ids List(str

要检索的文档 ID

 必需的
源代码位于 llama-index-integrations/tools/llama-index-tools-metaphor/llama_index/tools/metaphor/base.py 
65
66
67
68
69
70
71
72
73
74
def retrieve_documents(self, ids: List[str]) -> List[Document]:
    """
    Retrieve a list of document summaries returned by `metaphor_search`, using the ID field.

    Args:
        ids (List(str)): the ids of the documents to retrieve

    """
    response = self.client.get_contents(ids)
    return [Document(text=con.extract) for con in response.contents]

find_similar #

find_similar(url: str, num_results: Optional[int] = 3, start_published_date: Optional[str] = None, end_published_date: Optional[str] = None) -> str

检索与给定 URL 相似的文档列表。

参数

名称 类型 描述 默认值
url str

要查找相似结果的网页

 必需的
num_results Optional[int]

返回结果的数量。默认为 3。

 3
start_published_date Optional[str]

日期字符串，例如 “2020-06-15”

 无
end_published_date Optional[str]

结束日期字符串

 无
源代码位于 llama-index-integrations/tools/llama-index-tools-metaphor/llama_index/tools/metaphor/base.py 
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
def find_similar(
    self,
    url: str,
    num_results: Optional[int] = 3,
    start_published_date: Optional[str] = None,
    end_published_date: Optional[str] = None,
) -> str:
    """
    Retrieve a list of similar documents to a given url.

    Args:
        url (str): The web page to find similar results of
        num_results (Optional[int]): Number of results to return. Default 3.
        start_published_date (Optional[str]): A date string like "2020-06-15"
        end_published_date (Optional[str]): End date string

    """
    response = self.client.find_similar(
        url,
        num_results=num_results,
        start_published_date=start_published_date,
        end_published_date=end_published_date,
    )
    return [
        {"title": result.title, "url": result.url, "id": result.id}
        for result in response.results
    ]

search_and_retrieve_documents #

search_and_retrieve_documents(query: str, num_results: Optional[int] = 10, include_domains: Optional[List[str]] = None, exclude_domains: Optional[List[str]] = None, start_published_date: Optional[str] = None, end_published_date: Optional[str] = None) -> str

结合了 search 和 retrieve_documents 的功能。

参数

名称 类型 描述 默认值
query str

自然语言查询

 必需的
num_results Optional[int]

结果数量。默认为 10。

 10
include_domains Optional[List(str)]

要搜索的顶级域名列表，例如 ["wsj.com"]

 无
exclude_domains Optional[List(str)]

要排除的顶级域名。

 无
start_published_date Optional[str]

日期字符串，例如 “2020-06-15”。

 无
end_published_date Optional[str]

结束日期字符串

 无
源代码位于 llama-index-integrations/tools/llama-index-tools-metaphor/llama_index/tools/metaphor/base.py 
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
def search_and_retrieve_documents(
    self,
    query: str,
    num_results: Optional[int] = 10,
    include_domains: Optional[List[str]] = None,
    exclude_domains: Optional[List[str]] = None,
    start_published_date: Optional[str] = None,
    end_published_date: Optional[str] = None,
) -> str:
    """
    Combines the functionality of `search` and `retrieve_documents`.

    Args:
        query (str): the natural language query
        num_results (Optional[int]): Number of results. Defaults to 10.
        include_domains (Optional[List(str)]): A list of top level domains to search, like ["wsj.com"]
        exclude_domains (Optional[List(str)]): Top level domains to exclude.
        start_published_date (Optional[str]): A date string like "2020-06-15".
        end_published_date (Optional[str]): End date string

    """
    response = self.client.search(
        query,
        num_results=num_results,
        include_domains=include_domains,
        exclude_domains=exclude_domains,
        start_published_date=start_published_date,
        end_published_date=end_published_date,
        use_autoprompt=True,
    )
    if self._verbose:
        print(f"[Metaphor Tool] Autoprompt: {response.autoprompt_string}")
    ids = [result.id for result in response.results]
    documents = self.client.get_contents(ids)
    return [Document(text=document.extract) for document in documents.contents]

current_date #

current_date()

一个返回今天日期的函数。在调用任何其他接受时间戳作为参数的函数之前调用此函数。

源代码位于 llama-index-integrations/tools/llama-index-tools-metaphor/llama_index/tools/metaphor/base.py 
140
141
142
143
144
145
def current_date(self):
    """
    A function to return todays date.
    Call this before any other functions that take timestamps as an argument.
    """
    return datetime.date.today()