File size: 14,249 Bytes
63deadc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
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
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
"""**Retriever** class returns Documents given a text **query**.

It is more general than a vector store. A retriever does not need to be able to
store documents, only to return (or retrieve) it. Vector stores can be used as
the backbone of a retriever, but there are other types of retrievers as well.

**Class hierarchy:**

.. code-block::

    BaseRetriever --> <name>Retriever  # Examples: ArxivRetriever, MergerRetriever

**Main helpers:**

.. code-block::

    RetrieverInput, RetrieverOutput, RetrieverLike, RetrieverOutputLike,
    Document, Serializable, Callbacks,
    CallbackManagerForRetrieverRun, AsyncCallbackManagerForRetrieverRun
"""
from __future__ import annotations

import warnings
from abc import ABC, abstractmethod
from inspect import signature
from typing import TYPE_CHECKING, Any, Dict, List, Optional

from langchain_core._api import deprecated
from langchain_core.documents import Document
from langchain_core.load.dump import dumpd
from langchain_core.runnables import (
    Runnable,
    RunnableConfig,
    RunnableSerializable,
    ensure_config,
)
from langchain_core.runnables.config import run_in_executor

if TYPE_CHECKING:
    from langchain_core.callbacks.manager import (
        AsyncCallbackManagerForRetrieverRun,
        CallbackManagerForRetrieverRun,
        Callbacks,
    )

RetrieverInput = str
RetrieverOutput = List[Document]
RetrieverLike = Runnable[RetrieverInput, RetrieverOutput]
RetrieverOutputLike = Runnable[Any, RetrieverOutput]


class BaseRetriever(RunnableSerializable[RetrieverInput, RetrieverOutput], ABC):
    """Abstract base class for a Document retrieval system.


    A retrieval system is defined as something that can take string queries and return
    the most 'relevant' Documents from some source.

    Usage:

    A retriever follows the standard Runnable interface, and should be used
    via the standard runnable methods of `invoke`, `ainvoke`, `batch`, `abatch`.

    Implementation:

    When implementing a custom retriever, the class should implement
    the `_get_relevant_documents` method to define the logic for retrieving documents.

    Optionally, an async native implementations can be provided by overriding the
    `_aget_relevant_documents` method.

    Example: A retriever that returns the first 5 documents from a list of documents

        .. code-block:: python

            from langchain_core import Document, BaseRetriever
            from typing import List

            class SimpleRetriever(BaseRetriever):
                docs: List[Document]
                k: int = 5

                def _get_relevant_documents(self, query: str) -> List[Document]:
                    \"\"\"Return the first k documents from the list of documents\"\"\"
                    return self.docs[:self.k]

                async def _aget_relevant_documents(self, query: str) -> List[Document]:
                    \"\"\"(Optional) async native implementation.\"\"\"
                    return self.docs[:self.k]

    Example: A simple retriever based on a scitkit learn vectorizer

        .. code-block:: python

            from sklearn.metrics.pairwise import cosine_similarity

            class TFIDFRetriever(BaseRetriever, BaseModel):
                vectorizer: Any
                docs: List[Document]
                tfidf_array: Any
                k: int = 4

                class Config:
                    arbitrary_types_allowed = True

                def _get_relevant_documents(self, query: str) -> List[Document]:
                    # Ip -- (n_docs,x), Op -- (n_docs,n_Feats)
                    query_vec = self.vectorizer.transform([query])
                    # Op -- (n_docs,1) -- Cosine Sim with each doc
                    results = cosine_similarity(self.tfidf_array, query_vec).reshape((-1,))
                    return [self.docs[i] for i in results.argsort()[-self.k :][::-1]]
    """  # noqa: E501

    class Config:
        """Configuration for this pydantic object."""

        arbitrary_types_allowed = True

    _new_arg_supported: bool = False
    _expects_other_args: bool = False
    tags: Optional[List[str]] = None
    """Optional list of tags associated with the retriever. Defaults to None
    These tags will be associated with each call to this retriever,
    and passed as arguments to the handlers defined in `callbacks`.
    You can use these to eg identify a specific instance of a retriever with its 
    use case.
    """
    metadata: Optional[Dict[str, Any]] = None
    """Optional metadata associated with the retriever. Defaults to None
    This metadata will be associated with each call to this retriever,
    and passed as arguments to the handlers defined in `callbacks`.
    You can use these to eg identify a specific instance of a retriever with its 
    use case.
    """

    def __init_subclass__(cls, **kwargs: Any) -> None:
        super().__init_subclass__(**kwargs)
        # Version upgrade for old retrievers that implemented the public
        # methods directly.
        if cls.get_relevant_documents != BaseRetriever.get_relevant_documents:
            warnings.warn(
                "Retrievers must implement abstract `_get_relevant_documents` method"
                " instead of `get_relevant_documents`",
                DeprecationWarning,
            )
            swap = cls.get_relevant_documents
            cls.get_relevant_documents = (  # type: ignore[assignment]
                BaseRetriever.get_relevant_documents
            )
            cls._get_relevant_documents = swap  # type: ignore[assignment]
        if (
            hasattr(cls, "aget_relevant_documents")
            and cls.aget_relevant_documents != BaseRetriever.aget_relevant_documents
        ):
            warnings.warn(
                "Retrievers must implement abstract `_aget_relevant_documents` method"
                " instead of `aget_relevant_documents`",
                DeprecationWarning,
            )
            aswap = cls.aget_relevant_documents
            cls.aget_relevant_documents = (  # type: ignore[assignment]
                BaseRetriever.aget_relevant_documents
            )
            cls._aget_relevant_documents = aswap  # type: ignore[assignment]
        parameters = signature(cls._get_relevant_documents).parameters
        cls._new_arg_supported = parameters.get("run_manager") is not None
        # If a V1 retriever broke the interface and expects additional arguments
        cls._expects_other_args = (
            len(set(parameters.keys()) - {"self", "query", "run_manager"}) > 0
        )

    def invoke(
        self, input: str, config: Optional[RunnableConfig] = None, **kwargs: Any
    ) -> List[Document]:
        """Invoke the retriever to get relevant documents.

        Main entry point for synchronous retriever invocations.

        Args:
            input: The query string
            config: Configuration for the retriever
            **kwargs: Additional arguments to pass to the retriever

        Returns:
            List of relevant documents

        Examples:

        .. code-block:: python

            retriever.invoke("query")
        """
        config = ensure_config(config)
        return self.get_relevant_documents(
            input,
            callbacks=config.get("callbacks"),
            tags=config.get("tags"),
            metadata=config.get("metadata"),
            run_name=config.get("run_name"),
            **kwargs,
        )

    async def ainvoke(
        self,
        input: str,
        config: Optional[RunnableConfig] = None,
        **kwargs: Any,
    ) -> List[Document]:
        """Asynchronously invoke the retriever to get relevant documents.

        Main entry point for asynchronous retriever invocations.

        Args:
            input: The query string
            config: Configuration for the retriever
            **kwargs: Additional arguments to pass to the retriever

        Returns:
            List of relevant documents

        Examples:

        .. code-block:: python

            await retriever.ainvoke("query")
        """
        config = ensure_config(config)
        return await self.aget_relevant_documents(
            input,
            callbacks=config.get("callbacks"),
            tags=config.get("tags"),
            metadata=config.get("metadata"),
            run_name=config.get("run_name"),
            **kwargs,
        )

    @abstractmethod
    def _get_relevant_documents(
        self, query: str, *, run_manager: CallbackManagerForRetrieverRun
    ) -> List[Document]:
        """Get documents relevant to a query.
        Args:
            query: String to find relevant documents for
            run_manager: The callbacks handler to use
        Returns:
            List of relevant documents
        """

    async def _aget_relevant_documents(
        self, query: str, *, run_manager: AsyncCallbackManagerForRetrieverRun
    ) -> List[Document]:
        """Asynchronously get documents relevant to a query.
        Args:
            query: String to find relevant documents for
            run_manager: The callbacks handler to use
        Returns:
            List of relevant documents
        """
        return await run_in_executor(
            None,
            self._get_relevant_documents,
            query,
            run_manager=run_manager.get_sync(),
        )

    @deprecated(since="0.1.46", alternative="invoke", removal="0.3.0")
    def get_relevant_documents(
        self,
        query: str,
        *,
        callbacks: Callbacks = None,
        tags: Optional[List[str]] = None,
        metadata: Optional[Dict[str, Any]] = None,
        run_name: Optional[str] = None,
        **kwargs: Any,
    ) -> List[Document]:
        """Retrieve documents relevant to a query.

        Users should favor using `.invoke` or `.batch` rather than
        `get_relevant_documents directly`.

        Args:
            query: string to find relevant documents for
            callbacks: Callback manager or list of callbacks
            tags: Optional list of tags associated with the retriever. Defaults to None
                These tags will be associated with each call to this retriever,
                and passed as arguments to the handlers defined in `callbacks`.
            metadata: Optional metadata associated with the retriever. Defaults to None
                This metadata will be associated with each call to this retriever,
                and passed as arguments to the handlers defined in `callbacks`.
            run_name: Optional name for the run.

        Returns:
            List of relevant documents
        """
        from langchain_core.callbacks.manager import CallbackManager

        callback_manager = CallbackManager.configure(
            callbacks,
            None,
            verbose=kwargs.get("verbose", False),
            inheritable_tags=tags,
            local_tags=self.tags,
            inheritable_metadata=metadata,
            local_metadata=self.metadata,
        )
        run_manager = callback_manager.on_retriever_start(
            dumpd(self),
            query,
            name=run_name,
            run_id=kwargs.pop("run_id", None),
        )
        try:
            _kwargs = kwargs if self._expects_other_args else {}
            if self._new_arg_supported:
                result = self._get_relevant_documents(
                    query, run_manager=run_manager, **_kwargs
                )
            else:
                result = self._get_relevant_documents(query, **_kwargs)
        except Exception as e:
            run_manager.on_retriever_error(e)
            raise e
        else:
            run_manager.on_retriever_end(
                result,
            )
            return result

    @deprecated(since="0.1.46", alternative="ainvoke", removal="0.3.0")
    async def aget_relevant_documents(
        self,
        query: str,
        *,
        callbacks: Callbacks = None,
        tags: Optional[List[str]] = None,
        metadata: Optional[Dict[str, Any]] = None,
        run_name: Optional[str] = None,
        **kwargs: Any,
    ) -> List[Document]:
        """Asynchronously get documents relevant to a query.

        Users should favor using `.ainvoke` or `.abatch` rather than
        `aget_relevant_documents directly`.

        Args:
            query: string to find relevant documents for
            callbacks: Callback manager or list of callbacks
            tags: Optional list of tags associated with the retriever. Defaults to None
                These tags will be associated with each call to this retriever,
                and passed as arguments to the handlers defined in `callbacks`.
            metadata: Optional metadata associated with the retriever. Defaults to None
                This metadata will be associated with each call to this retriever,
                and passed as arguments to the handlers defined in `callbacks`.
            run_name: Optional name for the run.

        Returns:
            List of relevant documents
        """
        from langchain_core.callbacks.manager import AsyncCallbackManager

        callback_manager = AsyncCallbackManager.configure(
            callbacks,
            None,
            verbose=kwargs.get("verbose", False),
            inheritable_tags=tags,
            local_tags=self.tags,
            inheritable_metadata=metadata,
            local_metadata=self.metadata,
        )
        run_manager = await callback_manager.on_retriever_start(
            dumpd(self),
            query,
            name=run_name,
            run_id=kwargs.pop("run_id", None),
        )
        try:
            _kwargs = kwargs if self._expects_other_args else {}
            if self._new_arg_supported:
                result = await self._aget_relevant_documents(
                    query, run_manager=run_manager, **_kwargs
                )
            else:
                result = await self._aget_relevant_documents(query, **_kwargs)
        except Exception as e:
            await run_manager.on_retriever_error(e)
            raise e
        else:
            await run_manager.on_retriever_end(
                result,
            )
            return result