semantic_router.index.postgres.PostgresIndex#

class semantic_router.index.postgres.PostgresIndex(connection_string: str | None = None, index_prefix: str = 'semantic_router_', index_name: str = 'index', dimensions: int = 1536, metric: Metric = Metric.COSINE, namespace: str | None = '')#

Bases: BaseIndex

Postgres implementation of Index.

__init__(connection_string: str | None = None, index_prefix: str = 'semantic_router_', index_name: str = 'index', dimensions: int = 1536, metric: Metric = Metric.COSINE, namespace: str | None = '')#

Initializes the Postgres index with the specified parameters.

Parameters:
  • connection_string (Optional[str]) – The connection string for the PostgreSQL database.

  • index_prefix (str) – The prefix for the index table name.

  • index_name (str) – The name of the index table.

  • dimensions (int) – The number of dimensions for the vectors.

  • metric (Metric) – The metric used for vector comparisons.

  • namespace (Optional[str]) – An optional namespace for the index.

Methods

__init__([connection_string, index_prefix, ...])

Initializes the Postgres index with the specified parameters.

add(embeddings, routes, utterances[, ...])

Adds vectors to the index.

aget_routes()

Asynchronously get a list of route and utterance objects currently stored in the index.

aquery(vector[, top_k, route_filter])

Search the index for the query_vector and return top_k results.

construct([_fields_set])

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data.

copy(*[, include, exclude, update, deep])

Duplicate a model, optionally choose which fields to include, exclude and change.

delete(route_name)

Deletes records with the specified route name.

delete_all()

Deletes all records from the Postgres index.

delete_index()

Deletes the entire table for the index.

describe()

Describes the index by returning its type, dimensions, and total vector count.

dict(*[, include, exclude, by_alias, ...])

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

from_orm(obj)

get_routes()

Gets a list of route objects currently stored in the index.

get_utterances()

Gets a list of route and utterance objects currently stored in the index, including additional metadata.

json(*[, include, exclude, by_alias, ...])

Generate a JSON representation of the model, include and exclude arguments as per dict().

parse_file(path, *[, content_type, ...])

parse_obj(obj)

parse_raw(b, *[, content_type, encoding, ...])

query(vector[, top_k, route_filter])

Searches the index for the query vector and returns the top_k results.

schema([by_alias, ref_template])

schema_json(*[, by_alias, ref_template])

setup_index()

Sets up the index by creating the table and vector extension if they do not exist.

update_forward_refs(**localns)

Try to update ForwardRefs on fields based on this Model, globalns and localns.

validate(value)

Attributes

connection_string

index_prefix

index_name

dimensions

metric

namespace

conn

type

index

routes

utterances

init_async_index

class Config#

Bases: object

Configuration for the Pydantic BaseModel.

add(embeddings: List[List[float]], routes: List[str], utterances: List[str], function_schemas: List[Dict[str, Any]] | None = None, metadata_list: List[Dict[str, Any]] = []) None#

Adds vectors to the index.

Parameters:
  • embeddings (List[List[float]]) – A list of vector embeddings to add.

  • routes (List[str]) – A list of route names corresponding to the embeddings.

  • utterances (List[Any]) – A list of utterances corresponding to the embeddings.

Raises:
  • ValueError – If the vector embeddings being added do not match the expected dimensions.

  • TypeError – If the database connection is not established.

aget_routes()#

Asynchronously get a list of route and utterance objects currently stored in the index. This method should be implemented by subclasses.

Returns:

A list of tuples, each containing a route name and an associated utterance.

Return type:

list[tuple]

Raises:

NotImplementedError – If the method is not implemented by the subclass.

async aquery(vector: ndarray, top_k: int = 5, route_filter: List[str] | None = None) Tuple[ndarray, List[str]]#

Search the index for the query_vector and return top_k results. This method should be implemented by subclasses.

classmethod construct(_fields_set: SetStr | None = None, **values: Any) Model#

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values

copy(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, update: DictStrAny | None = None, deep: bool = False) Model#

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters:
  • include – fields to include in new model

  • exclude – fields to exclude from new model, as with values this takes precedence over include

  • update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

  • deep – set to True to make a deep copy of the model

Returns:

new model instance

delete(route_name: str) None#

Deletes records with the specified route name.

Parameters:

route_name (str) – The name of the route to delete records for.

Raises:

TypeError – If the database connection is not established.

delete_all()#

Deletes all records from the Postgres index.

Raises:

TypeError – If the database connection is not established.

delete_index() None#

Deletes the entire table for the index.

Raises:

TypeError – If the database connection is not established.

describe() Dict#

Describes the index by returning its type, dimensions, and total vector count.

Returns:

A dictionary containing the index’s type, dimensions, and total vector count.

Return type:

Dict

Raises:

TypeError – If the database connection is not established.

dict(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, by_alias: bool = False, skip_defaults: bool | None = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) DictStrAny#

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

get_routes() List[Route]#

Gets a list of route objects currently stored in the index.

Returns:

A list of Route objects.

Return type:

List[Route]

get_utterances() List[Utterance]#

Gets a list of route and utterance objects currently stored in the index, including additional metadata.

Returns:

A list of tuples, each containing route, utterance, function

schema and additional metadata. :rtype: List[Tuple]

json(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, by_alias: bool = False, skip_defaults: bool | None = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Callable[[Any], Any] | None = None, models_as_dict: bool = True, **dumps_kwargs: Any) str#

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

query(vector: ndarray, top_k: int = 5, route_filter: List[str] | None = None) Tuple[ndarray, List[str]]#

Searches the index for the query vector and returns the top_k results.

Parameters:
  • vector (np.ndarray) – The query vector.

  • top_k (int) – The number of top results to return.

  • route_filter (Optional[List[str]]) – Optional list of routes to filter the results by.

Returns:

A tuple containing the scores and routes of the top_k results.

Return type:

Tuple[np.ndarray, List[str]]

Raises:

TypeError – If the database connection is not established.

setup_index() None#

Sets up the index by creating the table and vector extension if they do not exist.

Raises:
  • ValueError – If the existing table’s vector dimensions do not match the expected dimensions.

  • TypeError – If the database connection is not established.

classmethod update_forward_refs(**localns: Any) None#

Try to update ForwardRefs on fields based on this Model, globalns and localns.