File size: 10,197 Bytes
58d33f0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""Wrapper around ChromaDB embeddings platform."""
from __future__ import annotations

import logging
import uuid
from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Tuple

from langchain.docstore.document import Document
from langchain.embeddings.base import Embeddings
from langchain.vectorstores.base import VectorStore

if TYPE_CHECKING:
    import chromadb
    import chromadb.config

logger = logging.getLogger()


def _results_to_docs(results: Any) -> List[Document]:
    return [doc for doc, _ in _results_to_docs_and_scores(results)]


def _results_to_docs_and_scores(results: Any) -> List[Tuple[Document, float]]:
    return [
        # TODO: Chroma can do batch querying,
        # we shouldn't hard code to the 1st result
        (Document(page_content=result[0], metadata=result[1] or {}), result[2])
        for result in zip(
            results["documents"][0],
            results["metadatas"][0],
            results["distances"][0],
        )
    ]


class Chroma(VectorStore):
    """Wrapper around ChromaDB embeddings platform.

    To use, you should have the ``chromadb`` python package installed.

    Example:
        .. code-block:: python

                from langchain.vectorstores import Chroma
                from langchain.embeddings.openai import OpenAIEmbeddings

                embeddings = OpenAIEmbeddings()
                vectorstore = Chroma("langchain_store", embeddings.embed_query)
    """

    _LANGCHAIN_DEFAULT_COLLECTION_NAME = "langchain"

    def __init__(
        self,
        collection_name: str = _LANGCHAIN_DEFAULT_COLLECTION_NAME,
        embedding_function: Optional[Embeddings] = None,
        persist_directory: Optional[str] = None,
        client_settings: Optional[chromadb.config.Settings] = None,
    ) -> None:
        """Initialize with Chroma client."""
        try:
            import chromadb
            import chromadb.config
        except ImportError:
            raise ValueError(
                "Could not import chromadb python package. "
                "Please install it with `pip install chromadb`."
            )

        if client_settings:
            self._client_settings = client_settings
        else:
            self._client_settings = chromadb.config.Settings()
            if persist_directory is not None:
                self._client_settings = chromadb.config.Settings(
                    chroma_db_impl="duckdb+parquet", persist_directory=persist_directory
                )
        self._client = chromadb.Client(self._client_settings)
        self._embedding_function = embedding_function
        self._persist_directory = persist_directory
        self._collection = self._client.get_or_create_collection(
            name=collection_name,
            embedding_function=self._embedding_function.embed_documents
            if self._embedding_function is not None
            else None,
        )

    def add_texts(
        self,
        texts: Iterable[str],
        metadatas: Optional[List[dict]] = None,
        ids: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> List[str]:
        """Run more texts through the embeddings and add to the vectorstore.

        Args:
            texts (Iterable[str]): Texts to add to the vectorstore.
            metadatas (Optional[List[dict]], optional): Optional list of metadatas.
            ids (Optional[List[str]], optional): Optional list of IDs.

        Returns:
            List[str]: List of IDs of the added texts.
        """
        # TODO: Handle the case where the user doesn't provide ids on the Collection
        if ids is None:
            ids = [str(uuid.uuid1()) for _ in texts]
        embeddings = None
        if self._embedding_function is not None:
            embeddings = self._embedding_function.embed_documents(list(texts))
        self._collection.add(
            metadatas=metadatas, embeddings=embeddings, documents=texts, ids=ids
        )
        return ids

    def similarity_search(
        self,
        query: str,
        k: int = 4,
        filter: Optional[Dict[str, str]] = None,
        **kwargs: Any,
    ) -> List[Document]:
        """Run similarity search with Chroma.

        Args:
            query (str): Query text to search for.
            k (int): Number of results to return. Defaults to 4.
            filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None.

        Returns:
            List[Document]: List of documents most simmilar to the query text.
        """
        docs_and_scores = self.similarity_search_with_score(query, k, where=filter)
        return [doc for doc, _ in docs_and_scores]

    def similarity_search_by_vector(
        self,
        embedding: List[float],
        k: int = 4,
        filter: Optional[Dict[str, str]] = None,
        **kwargs: Any,
    ) -> List[Document]:
        """Return docs most similar to embedding vector.
        Args:
            embedding: Embedding to look up documents similar to.
            k: Number of Documents to return. Defaults to 4.
        Returns:
            List of Documents most similar to the query vector.
        """
        results = self._collection.query(
            query_embeddings=embedding, n_results=k, where=filter
        )
        return _results_to_docs(results)

    def similarity_search_with_score(
        self,
        query: str,
        k: int = 4,
        filter: Optional[Dict[str, str]] = None,
        **kwargs: Any,
    ) -> List[Tuple[Document, float]]:
        """Run similarity search with Chroma with distance.

        Args:
            query (str): Query text to search for.
            k (int): Number of results to return. Defaults to 4.
            filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None.

        Returns:
            List[Tuple[Document, float]]: List of documents most similar to the query
                text with distance in float.
        """
        if self._embedding_function is None:
            results = self._collection.query(
                query_texts=[query], n_results=k, where=filter
            )
        else:
            query_embedding = self._embedding_function.embed_query(query)
            results = self._collection.query(
                query_embeddings=[query_embedding], n_results=k, where=filter
            )

        return _results_to_docs_and_scores(results)

    def delete_collection(self) -> None:
        """Delete the collection."""
        self._client.delete_collection(self._collection.name)

    def persist(self) -> None:
        """Persist the collection.

        This can be used to explicitly persist the data to disk.
        It will also be called automatically when the object is destroyed.
        """
        if self._persist_directory is None:
            raise ValueError(
                "You must specify a persist_directory on"
                "creation to persist the collection."
            )
        self._client.persist()

    @classmethod
    def from_texts(
        cls,
        texts: List[str],
        embedding: Optional[Embeddings] = None,
        metadatas: Optional[List[dict]] = None,
        ids: Optional[List[str]] = None,
        collection_name: str = _LANGCHAIN_DEFAULT_COLLECTION_NAME,
        persist_directory: Optional[str] = None,
        client_settings: Optional[chromadb.config.Settings] = None,
        **kwargs: Any,
    ) -> Chroma:
        """Create a Chroma vectorstore from a raw documents.

        If a persist_directory is specified, the collection will be persisted there.
        Otherwise, the data will be ephemeral in-memory.

        Args:
            texts (List[str]): List of texts to add to the collection.
            collection_name (str): Name of the collection to create.
            persist_directory (Optional[str]): Directory to persist the collection.
            embedding (Optional[Embeddings]): Embedding function. Defaults to None.
            metadatas (Optional[List[dict]]): List of metadatas. Defaults to None.
            ids (Optional[List[str]]): List of document IDs. Defaults to None.
            client_settings (Optional[chromadb.config.Settings]): Chroma client settings

        Returns:
            Chroma: Chroma vectorstore.
        """
        chroma_collection = cls(
            collection_name=collection_name,
            embedding_function=embedding,
            persist_directory=persist_directory,
            client_settings=client_settings,
        )
        chroma_collection.add_texts(texts=texts, metadatas=metadatas, ids=ids)
        return chroma_collection

    @classmethod
    def from_documents(
        cls,
        documents: List[Document],
        embedding: Optional[Embeddings] = None,
        ids: Optional[List[str]] = None,
        collection_name: str = _LANGCHAIN_DEFAULT_COLLECTION_NAME,
        persist_directory: Optional[str] = None,
        client_settings: Optional[chromadb.config.Settings] = None,
        **kwargs: Any,
    ) -> Chroma:
        """Create a Chroma vectorstore from a list of documents.

        If a persist_directory is specified, the collection will be persisted there.
        Otherwise, the data will be ephemeral in-memory.

        Args:
            collection_name (str): Name of the collection to create.
            persist_directory (Optional[str]): Directory to persist the collection.
            ids (Optional[List[str]]): List of document IDs. Defaults to None.
            documents (List[Document]): List of documents to add to the vectorstore.
            embedding (Optional[Embeddings]): Embedding function. Defaults to None.
            client_settings (Optional[chromadb.config.Settings]): Chroma client settings
        Returns:
            Chroma: Chroma vectorstore.
        """
        texts = [doc.page_content for doc in documents]
        metadatas = [doc.metadata for doc in documents]
        return cls.from_texts(
            texts=texts,
            embedding=embedding,
            metadatas=metadatas,
            ids=ids,
            collection_name=collection_name,
            persist_directory=persist_directory,
            client_settings=client_settings,
        )