From 5019951a5d31676e61f314b35d5e199a605405d0 Mon Sep 17 00:00:00 2001 From: Christophe Bornet Date: Thu, 22 Feb 2024 01:16:31 +0100 Subject: [PATCH] docs: AstraDB VectorStore docstring (#17834) --- .../vectorstores/astradb.py | 449 +++++++++++------- 1 file changed, 280 insertions(+), 169 deletions(-) diff --git a/libs/community/langchain_community/vectorstores/astradb.py b/libs/community/langchain_community/vectorstores/astradb.py index 67751e4410..da9ed439a3 100644 --- a/libs/community/langchain_community/vectorstores/astradb.py +++ b/libs/community/langchain_community/vectorstores/astradb.py @@ -71,73 +71,6 @@ def _unique_list(lst: List[T], key: Callable[[T], U]) -> List[T]: alternative_import="langchain_astradb.AstraDBVectorStore", ) class AstraDB(VectorStore): - """Wrapper around DataStax Astra DB for vector-store workloads. - - To use it, you need a recent installation of the `astrapy` library - and an Astra DB cloud database. - - For quickstart and details, visit: - docs.datastax.com/en/astra/home/astra.html - - Example: - .. code-block:: python - - from langchain_community.vectorstores import AstraDB - from langchain_community.embeddings.openai import OpenAIEmbeddings - - embeddings = OpenAIEmbeddings() - vectorstore = AstraDB( - embedding=embeddings, - collection_name="my_store", - token="AstraCS:...", - api_endpoint="https://-us-east1.apps.astra.datastax.com" - ) - - vectorstore.add_texts(["Giraffes", "All good here"]) - results = vectorstore.similarity_search("Everything's ok", k=1) - - Constructor Args (only keyword-arguments accepted): - embedding (Embeddings): embedding function to use. - collection_name (str): name of the Astra DB collection to create/use. - token (Optional[str]): API token for Astra DB usage. - api_endpoint (Optional[str]): full URL to the API endpoint, - such as "https://-us-east1.apps.astra.datastax.com". - astra_db_client (Optional[Any]): *alternative to token+api_endpoint*, - you can pass an already-created 'astrapy.db.AstraDB' instance. - namespace (Optional[str]): namespace (aka keyspace) where the - collection is created. Defaults to the database's "default namespace". - metric (Optional[str]): similarity function to use out of those - available in Astra DB. If left out, it will use Astra DB API's - defaults (i.e. "cosine" - but, for performance reasons, - "dot_product" is suggested if embeddings are normalized to one). - - Advanced arguments (coming with sensible defaults): - batch_size (Optional[int]): Size of batches for bulk insertions. - bulk_insert_batch_concurrency (Optional[int]): Number of threads - to insert batches concurrently. - bulk_insert_overwrite_concurrency (Optional[int]): Number of - threads in a batch to insert pre-existing entries. - bulk_delete_concurrency (Optional[int]): Number of threads - (for deleting multiple rows concurrently). - pre_delete_collection (Optional[bool]): whether to delete the collection - before creating it. If False and the collection already exists, - the collection will be used as is. - - A note on concurrency: as a rule of thumb, on a typical client machine - it is suggested to keep the quantity - bulk_insert_batch_concurrency * bulk_insert_overwrite_concurrency - much below 1000 to avoid exhausting the client multithreading/networking - resources. The hardcoded defaults are somewhat conservative to meet - most machines' specs, but a sensible choice to test may be: - bulk_insert_batch_concurrency = 80 - bulk_insert_overwrite_concurrency = 10 - A bit of experimentation is required to nail the best results here, - depending on both the machine/network specs and the expected workload - (specifically, how often a write is an update of an existing id). - Remember you can pass concurrency settings to individual calls to - add_texts and add_documents as well. - """ - @staticmethod def _filter_to_metadata(filter_dict: Optional[Dict[str, Any]]) -> Dict[str, Any]: if filter_dict is None: @@ -173,8 +106,71 @@ class AstraDB(VectorStore): setup_mode: SetupMode = SetupMode.SYNC, pre_delete_collection: bool = False, ) -> None: - """ - Create an AstraDB vector store object. See class docstring for help. + """Wrapper around DataStax Astra DB for vector-store workloads. + + For quickstart and details, visit + https://docs.datastax.com/en/astra/astra-db-vector/ + + Example: + .. code-block:: python + + from langchain_community.vectorstores import AstraDB + from langchain_openai.embeddings import OpenAIEmbeddings + + embeddings = OpenAIEmbeddings() + vectorstore = AstraDB( + embedding=embeddings, + collection_name="my_store", + token="AstraCS:...", + api_endpoint="https://-.apps.astra.datastax.com" + ) + + vectorstore.add_texts(["Giraffes", "All good here"]) + results = vectorstore.similarity_search("Everything's ok", k=1) + + Args: + embedding: embedding function to use. + collection_name: name of the Astra DB collection to create/use. + token: API token for Astra DB usage. + api_endpoint: full URL to the API endpoint, such as + `https://-us-east1.apps.astra.datastax.com`. + astra_db_client: *alternative to token+api_endpoint*, + you can pass an already-created 'astrapy.db.AstraDB' instance. + async_astra_db_client: *alternative to token+api_endpoint*, + you can pass an already-created 'astrapy.db.AsyncAstraDB' instance. + namespace: namespace (aka keyspace) where the collection is created. + Defaults to the database's "default namespace". + metric: similarity function to use out of those available in Astra DB. + If left out, it will use Astra DB API's defaults (i.e. "cosine" - but, + for performance reasons, "dot_product" is suggested if embeddings are + normalized to one). + batch_size: Size of batches for bulk insertions. + bulk_insert_batch_concurrency: Number of threads or coroutines to insert + batches concurrently. + bulk_insert_overwrite_concurrency: Number of threads or coroutines in a + batch to insert pre-existing entries. + bulk_delete_concurrency: Number of threads (for deleting multiple rows + concurrently). + pre_delete_collection: whether to delete the collection before creating it. + If False and the collection already exists, the collection will be used + as is. + + Note: + For concurrency in synchronous :meth:`~add_texts`:, as a rule of thumb, on a + typical client machine it is suggested to keep the quantity + bulk_insert_batch_concurrency * bulk_insert_overwrite_concurrency + much below 1000 to avoid exhausting the client multithreading/networking + resources. The hardcoded defaults are somewhat conservative to meet + most machines' specs, but a sensible choice to test may be: + + - bulk_insert_batch_concurrency = 80 + - bulk_insert_overwrite_concurrency = 10 + + A bit of experimentation is required to nail the best results here, + depending on both the machine/network specs and the expected workload + (specifically, how often a write is an update of an existing id). + Remember you can pass concurrency settings to individual calls to + :meth:`~add_texts` and :meth:`~add_documents` as well. """ self.embedding = embedding self.collection_name = collection_name @@ -253,8 +249,13 @@ class AstraDB(VectorStore): def delete_by_document_id(self, document_id: str) -> bool: """ - Remove a single document from the store, given its document_id (str). - Return True if a document has indeed been deleted, False if ID not found. + Remove a single document from the store, given its document ID. + + Args: + document_id: The document ID + + Returns + True if a document has indeed been deleted, False if ID not found. """ self.astra_env.ensure_db_setup() deletion_response = self.collection.delete_one(document_id) # type: ignore[union-attr] @@ -264,8 +265,13 @@ class AstraDB(VectorStore): async def adelete_by_document_id(self, document_id: str) -> bool: """ - Remove a single document from the store, given its document_id (str). - Return True if a document has indeed been deleted, False if ID not found. + Remove a single document from the store, given its document ID. + + Args: + document_id: The document ID + + Returns + True if a document has indeed been deleted, False if ID not found. """ await self.astra_env.aensure_db_setup() deletion_response = await self.async_collection.delete_one(document_id) @@ -282,13 +288,12 @@ class AstraDB(VectorStore): """Delete by vector ids. Args: - ids (Optional[List[str]]): List of ids to delete. - concurrency (Optional[int]): max number of threads issuing - single-doc delete requests. Defaults to instance-level setting. + ids: List of ids to delete. + concurrency: max number of threads issuing single-doc delete requests. + Defaults to instance-level setting. Returns: - Optional[bool]: True if deletion is successful, - False otherwise, None if not implemented. + True if deletion is successful, False otherwise. """ if kwargs: @@ -317,17 +322,16 @@ class AstraDB(VectorStore): concurrency: Optional[int] = None, **kwargs: Any, ) -> Optional[bool]: - """Delete by vector ID or other criteria. + """Delete by vector ids. Args: ids: List of ids to delete. - concurrency (Optional[int]): max number of concurrent delete queries. + concurrency: max concurrency of single-doc delete requests. Defaults to instance-level setting. **kwargs: Other keyword arguments that subclasses might use. Returns: - Optional[bool]: True if deletion is successful, - False otherwise, None if not implemented. + True if deletion is successful, False otherwise. """ if kwargs: warnings.warn( @@ -348,7 +352,7 @@ class AstraDB(VectorStore): def delete_collection(self) -> None: """ Completely delete the collection from the database (as opposed - to 'clear()', which empties it only). + to :meth:`~clear`, which empties it only). Stored data is lost and unrecoverable, resources are freed. Use with caution. """ @@ -360,7 +364,7 @@ class AstraDB(VectorStore): async def adelete_collection(self) -> None: """ Completely delete the collection from the database (as opposed - to 'clear()', which empties it only). + to :meth:`~aclear`, which empties it only). Stored data is lost and unrecoverable, resources are freed. Use with caution. """ @@ -450,28 +454,29 @@ class AstraDB(VectorStore): will be replaced. 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. - batch_size (Optional[int]): Number of documents in each API call. + texts: Texts to add to the vectorstore. + metadatas: Optional list of metadatas. + ids: Optional list of ids. + batch_size: Number of documents in each API call. Check the underlying Astra DB HTTP API specs for the max value (20 at the time of writing this). If not provided, defaults to the instance-level setting. - batch_concurrency (Optional[int]): number of threads to process + batch_concurrency: number of threads to process insertion batches concurrently. Defaults to instance-level setting if not provided. - overwrite_concurrency (Optional[int]): number of threads to process + overwrite_concurrency: number of threads to process pre-existing documents in each batch (which require individual API calls). Defaults to instance-level setting if not provided. - A note on metadata: there are constraints on the allowed field names - in this dictionary, coming from the underlying Astra DB API. - For instance, the `$` (dollar sign) cannot be used in the dict keys. - See this document for details: - docs.datastax.com/en/astra-serverless/docs/develop/dev-with-json.html + Note: + There are constraints on the allowed field names + in the metadata dictionaries, coming from the underlying Astra DB API. + For instance, the `$` (dollar sign) cannot be used in the dict keys. + See this document for details: + https://docs.datastax.com/en/astra/astra-db-vector/api-reference/data-api.html Returns: - List[str]: List of ids of the added texts. + The list of ids of the added texts. """ if kwargs: @@ -488,7 +493,7 @@ class AstraDB(VectorStore): ) def _handle_batch(document_batch: List[DocDict]) -> List[str]: - im_result = self.collection.insert_many( # type: ignore[union-attr] + im_result = self.collection.insert_many( documents=document_batch, options={"ordered": False}, partial_failures_allowed=True, @@ -498,7 +503,7 @@ class AstraDB(VectorStore): ) def _handle_missing_document(missing_document: DocDict) -> str: - replacement_result = self.collection.find_one_and_replace( # type: ignore[union-attr] + replacement_result = self.collection.find_one_and_replace( filter={"_id": missing_document["_id"]}, replacement=missing_document, ) @@ -544,27 +549,29 @@ class AstraDB(VectorStore): will be replaced. 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. - batch_size (Optional[int]): Number of documents in each API call. + texts: Texts to add to the vectorstore. + metadatas: Optional list of metadatas. + ids: Optional list of ids. + batch_size: Number of documents in each API call. Check the underlying Astra DB HTTP API specs for the max value (20 at the time of writing this). If not provided, defaults to the instance-level setting. - batch_concurrency (Optional[int]): number of concurrent batch insertions. - Defaults to instance-level setting if not provided. - overwrite_concurrency (Optional[int]): number of concurrent API calls to - process pre-existing documents in each batch. - Defaults to instance-level setting if not provided. - - A note on metadata: there are constraints on the allowed field names - in this dictionary, coming from the underlying Astra DB API. - For instance, the `$` (dollar sign) cannot be used in the dict keys. - See this document for details: - docs.datastax.com/en/astra-serverless/docs/develop/dev-with-json.html + batch_concurrency: number of threads to process + insertion batches concurrently. Defaults to instance-level + setting if not provided. + overwrite_concurrency: number of threads to process + pre-existing documents in each batch (which require individual + API calls). Defaults to instance-level setting if not provided. + + Note: + There are constraints on the allowed field names + in the metadata dictionaries, coming from the underlying Astra DB API. + For instance, the `$` (dollar sign) cannot be used in the dict keys. + See this document for details: + https://docs.datastax.com/en/astra/astra-db-vector/api-reference/data-api.html Returns: - List[str]: List of ids of the added texts. + The list of ids of the added texts. """ if kwargs: warnings.warn( @@ -580,7 +587,7 @@ class AstraDB(VectorStore): ) async def _handle_batch(document_batch: List[DocDict]) -> List[str]: - im_result = await self.async_collection.insert_many( # type: ignore[union-attr] + im_result = await self.async_collection.insert_many( documents=document_batch, options={"ordered": False}, partial_failures_allowed=True, @@ -590,7 +597,7 @@ class AstraDB(VectorStore): ) async def _handle_missing_document(missing_document: DocDict) -> str: - replacement_result = await self.async_collection.find_one_and_replace( # type: ignore[union-attr] + replacement_result = await self.async_collection.find_one_and_replace( filter={"_id": missing_document["_id"]}, replacement=missing_document, ) @@ -625,19 +632,21 @@ class AstraDB(VectorStore): k: int = 4, filter: Optional[Dict[str, Any]] = None, ) -> List[Tuple[Document, float, str]]: - """Return docs most similar to embedding vector. + """Return docs most similar to embedding vector with score and id. Args: - embedding (str): Embedding to look up documents similar to. - k (int): Number of Documents to return. Defaults to 4. + embedding: Embedding to look up documents similar to. + k: Number of Documents to return. Defaults to 4. + filter: Filter on the metadata to apply. + Returns: - List of (Document, score, id), the most similar to the query vector. + The list of (Document, score, id), the most similar to the query vector. """ self.astra_env.ensure_db_setup() metadata_parameter = self._filter_to_metadata(filter) # hits = list( - self.collection.paginated_find( # type: ignore[union-attr] + self.collection.paginated_find( filter=metadata_parameter, sort={"$vector": embedding}, options={"limit": k, "includeSimilarity": True}, @@ -667,13 +676,15 @@ class AstraDB(VectorStore): k: int = 4, filter: Optional[Dict[str, Any]] = None, ) -> List[Tuple[Document, float, str]]: - """Return docs most similar to embedding vector. + """Return docs most similar to embedding vector with score and id. Args: - embedding (str): Embedding to look up documents similar to. - k (int): Number of Documents to return. Defaults to 4. + embedding: Embedding to look up documents similar to. + k: Number of Documents to return. Defaults to 4. + filter: Filter on the metadata to apply. + Returns: - List of (Document, score, id), the most similar to the query vector. + The list of (Document, score, id), the most similar to the query vector. """ await self.astra_env.aensure_db_setup() metadata_parameter = self._filter_to_metadata(filter) @@ -705,6 +716,16 @@ class AstraDB(VectorStore): k: int = 4, filter: Optional[Dict[str, Any]] = None, ) -> List[Tuple[Document, float, str]]: + """Return docs most similar to the query with score and id. + + Args: + query: Query to look up documents similar to. + k: Number of Documents to return. Defaults to 4. + filter: Filter on the metadata to apply. + + Returns: + The list of (Document, score, id), the most similar to the query. + """ embedding_vector = self.embedding.embed_query(query) return self.similarity_search_with_score_id_by_vector( embedding=embedding_vector, @@ -718,6 +739,16 @@ class AstraDB(VectorStore): k: int = 4, filter: Optional[Dict[str, Any]] = None, ) -> List[Tuple[Document, float, str]]: + """Return docs most similar to the query with score and id. + + Args: + query: Query to look up documents similar to. + k: Number of Documents to return. Defaults to 4. + filter: Filter on the metadata to apply. + + Returns: + The list of (Document, score, id), the most similar to the query. + """ embedding_vector = await self.embedding.aembed_query(query) return await self.asimilarity_search_with_score_id_by_vector( embedding=embedding_vector, @@ -731,13 +762,15 @@ class AstraDB(VectorStore): k: int = 4, filter: Optional[Dict[str, Any]] = None, ) -> List[Tuple[Document, float]]: - """Return docs most similar to embedding vector. + """Return docs most similar to embedding vector with score. Args: - embedding (str): Embedding to look up documents similar to. - k (int): Number of Documents to return. Defaults to 4. + embedding: Embedding to look up documents similar to. + k: Number of Documents to return. Defaults to 4. + filter: Filter on the metadata to apply. + Returns: - List of (Document, score), the most similar to the query vector. + The list of (Document, score), the most similar to the query vector. """ return [ (doc, score) @@ -754,13 +787,15 @@ class AstraDB(VectorStore): k: int = 4, filter: Optional[Dict[str, Any]] = None, ) -> List[Tuple[Document, float]]: - """Return docs most similar to embedding vector. + """Return docs most similar to embedding vector with score. Args: - embedding (str): Embedding to look up documents similar to. - k (int): Number of Documents to return. Defaults to 4. + embedding: Embedding to look up documents similar to. + k: Number of Documents to return. Defaults to 4. + filter: Filter on the metadata to apply. + Returns: - List of (Document, score), the most similar to the query vector. + The list of (Document, score), the most similar to the query vector. """ return [ (doc, score) @@ -782,6 +817,16 @@ class AstraDB(VectorStore): filter: Optional[Dict[str, Any]] = None, **kwargs: Any, ) -> List[Document]: + """Return docs most similar to query. + + Args: + query: Query to look up documents similar to. + k: Number of Documents to return. Defaults to 4. + filter: Filter on the metadata to apply. + + Returns: + The list of Documents most similar to the query. + """ embedding_vector = self.embedding.embed_query(query) return self.similarity_search_by_vector( embedding_vector, @@ -796,6 +841,16 @@ class AstraDB(VectorStore): filter: Optional[Dict[str, Any]] = None, **kwargs: Any, ) -> List[Document]: + """Return docs most similar to query. + + Args: + query: Query to look up documents similar to. + k: Number of Documents to return. Defaults to 4. + filter: Filter on the metadata to apply. + + Returns: + The list of Documents most similar to the query. + """ embedding_vector = await self.embedding.aembed_query(query) return await self.asimilarity_search_by_vector( embedding_vector, @@ -810,6 +865,16 @@ class AstraDB(VectorStore): filter: Optional[Dict[str, Any]] = 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. + filter: Filter on the metadata to apply. + + Returns: + The list of Documents most similar to the query vector. + """ return [ doc for doc, _ in self.similarity_search_with_score_by_vector( @@ -826,6 +891,16 @@ class AstraDB(VectorStore): filter: Optional[Dict[str, Any]] = 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. + filter: Filter on the metadata to apply. + + Returns: + The list of Documents most similar to the query vector. + """ return [ doc for doc, _ in await self.asimilarity_search_with_score_by_vector( @@ -841,6 +916,16 @@ class AstraDB(VectorStore): k: int = 4, filter: Optional[Dict[str, Any]] = None, ) -> List[Tuple[Document, float]]: + """Return docs most similar to query with score. + + Args: + query: Query to look up documents similar to. + k: Number of Documents to return. Defaults to 4. + filter: Filter on the metadata to apply. + + Returns: + The list of (Document, score), the most similar to the query vector. + """ embedding_vector = self.embedding.embed_query(query) return self.similarity_search_with_score_by_vector( embedding_vector, @@ -854,6 +939,16 @@ class AstraDB(VectorStore): k: int = 4, filter: Optional[Dict[str, Any]] = None, ) -> List[Tuple[Document, float]]: + """Return docs most similar to query with score. + + Args: + query: Query to look up documents similar to. + k: Number of Documents to return. Defaults to 4. + filter: Filter on the metadata to apply. + + Returns: + The list of (Document, score), the most similar to the query vector. + """ embedding_vector = await self.embedding.aembed_query(query) return await self.asimilarity_search_with_score_by_vector( embedding_vector, @@ -862,7 +957,9 @@ class AstraDB(VectorStore): ) @staticmethod - def _get_mmr_hits(embedding, k, lambda_mult, prefetch_hits): # type: ignore[no-untyped-def] + def _get_mmr_hits( + embedding: List[float], k: int, lambda_mult: float, prefetch_hits: List[DocDict] + ) -> List[Document]: mmr_chosen_indices = maximal_marginal_relevance( np.array(embedding, dtype=np.float32), [prefetch_hit["$vector"] for prefetch_hit in prefetch_hits], @@ -892,23 +989,27 @@ class AstraDB(VectorStore): **kwargs: Any, ) -> List[Document]: """Return docs selected using the maximal marginal relevance. + Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. + Args: embedding: Embedding to look up documents similar to. k: Number of Documents to return. fetch_k: Number of Documents to fetch to pass to MMR algorithm. lambda_mult: Number between 0 and 1 that determines the degree - of diversity among the results with 0 corresponding - to maximum diversity and 1 to minimum diversity. + of diversity among the results with 0 corresponding + to maximum diversity and 1 to minimum diversity. + filter: Filter on the metadata to apply. + Returns: - List of Documents selected by maximal marginal relevance. + The list of Documents selected by maximal marginal relevance. """ self.astra_env.ensure_db_setup() metadata_parameter = self._filter_to_metadata(filter) prefetch_hits = list( - self.collection.paginated_find( # type: ignore[union-attr] + self.collection.paginated_find( filter=metadata_parameter, sort={"$vector": embedding}, options={"limit": fetch_k, "includeSimilarity": True}, @@ -933,17 +1034,21 @@ class AstraDB(VectorStore): **kwargs: Any, ) -> List[Document]: """Return docs selected using the maximal marginal relevance. + Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. + Args: embedding: Embedding to look up documents similar to. k: Number of Documents to return. fetch_k: Number of Documents to fetch to pass to MMR algorithm. lambda_mult: Number between 0 and 1 that determines the degree - of diversity among the results with 0 corresponding - to maximum diversity and 1 to minimum diversity. + of diversity among the results with 0 corresponding + to maximum diversity and 1 to minimum diversity. + filter: Filter on the metadata to apply. + Returns: - List of Documents selected by maximal marginal relevance. + The list of Documents selected by maximal marginal relevance. """ await self.astra_env.aensure_db_setup() metadata_parameter = self._filter_to_metadata(filter) @@ -975,18 +1080,21 @@ class AstraDB(VectorStore): **kwargs: Any, ) -> List[Document]: """Return docs selected using the maximal marginal relevance. + Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. + Args: - query (str): Text to look up documents similar to. - k (int = 4): Number of Documents to return. - fetch_k (int = 20): Number of Documents to fetch to pass to MMR algorithm. - lambda_mult (float = 0.5): Number between 0 and 1 that determines the degree - of diversity among the results with 0 corresponding - to maximum diversity and 1 to minimum diversity. - Optional. + query: Query to look up documents similar to. + k: Number of Documents to return. + fetch_k: Number of Documents to fetch to pass to MMR algorithm. + lambda_mult: Number between 0 and 1 that determines the degree + of diversity among the results with 0 corresponding + to maximum diversity and 1 to minimum diversity. + filter: Filter on the metadata to apply. + Returns: - List of Documents selected by maximal marginal relevance. + The list of Documents selected by maximal marginal relevance. """ embedding_vector = self.embedding.embed_query(query) return self.max_marginal_relevance_search_by_vector( @@ -1007,18 +1115,21 @@ class AstraDB(VectorStore): **kwargs: Any, ) -> List[Document]: """Return docs selected using the maximal marginal relevance. + Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. + Args: - query (str): Text to look up documents similar to. - k (int = 4): Number of Documents to return. - fetch_k (int = 20): Number of Documents to fetch to pass to MMR algorithm. - lambda_mult (float = 0.5): Number between 0 and 1 that determines the degree - of diversity among the results with 0 corresponding - to maximum diversity and 1 to minimum diversity. - Optional. + query: Query to look up documents similar to. + k: Number of Documents to return. + fetch_k: Number of Documents to fetch to pass to MMR algorithm. + lambda_mult: Number between 0 and 1 that determines the degree + of diversity among the results with 0 corresponding + to maximum diversity and 1 to minimum diversity. + filter: Filter on the metadata to apply. + Returns: - List of Documents selected by maximal marginal relevance. + The list of Documents selected by maximal marginal relevance. """ embedding_vector = await self.embedding.aembed_query(query) return await self.amax_marginal_relevance_search_by_vector( @@ -1096,12 +1207,12 @@ class AstraDB(VectorStore): """Create an Astra DB vectorstore from raw texts. Args: - texts (List[str]): the texts to insert. - embedding (Embeddings): the embedding function to use in the store. - metadatas (Optional[List[dict]]): metadata dicts for the texts. - ids (Optional[List[str]]): ids to associate to the texts. - *Additional arguments*: you can pass any argument that you would - to 'add_texts' and/or to the 'AstraDB' class constructor + texts: the texts to insert. + embedding: the embedding function to use in the store. + metadatas: metadata dicts for the texts. + ids: ids to associate to the texts. + **kwargs: you can pass any argument that you would + to :meth:`~add_texts` and/or to the 'AstraDB' constructor (see these methods for details). These arguments will be routed to the respective methods as they are. @@ -1131,12 +1242,12 @@ class AstraDB(VectorStore): """Create an Astra DB vectorstore from raw texts. Args: - texts (List[str]): the texts to insert. - embedding (Embeddings): the embedding function to use in the store. - metadatas (Optional[List[dict]]): metadata dicts for the texts. - ids (Optional[List[str]]): ids to associate to the texts. - *Additional arguments*: you can pass any argument that you would - to 'add_texts' and/or to the 'AstraDB' class constructor + texts: the texts to insert. + embedding: the embedding function to use in the store. + metadatas: metadata dicts for the texts. + ids: ids to associate to the texts. + **kwargs: you can pass any argument that you would + to :meth:`~add_texts` and/or to the 'AstraDB' constructor (see these methods for details). These arguments will be routed to the respective methods as they are.