Summary of entries of Classes for llama-index-alloydb-pg.
Classes
AlloyDBChatStore
Chat Store Table stored in an AlloyDB for PostgreSQL database.
AlloyDBDocumentStore
Document Store Table stored in an AlloyDB for PostgreSQL database.
AlloyDBEmbedding
Embedding model that generates embeddings inside AlloyDB.
Texts are embedded with the AlloyDB AI embedding(model_id, content)
function, so model_id must be a model registered with model endpoint
management, for example text-embedding-005. Each batch of
embed_batch_size texts is one SQL statement, and embedding() runs
once per row, so a larger batch saves round trips but not model calls.
An empty string raises ValueError. The batch methods check their whole
input, because LlamaIndex passes the hooks one batch at a time, so a hook
could not name the text's position.
The async batch methods embed num_workers batches at a time, each on its
own pool connection. DEFAULT_NUM_WORKERS (4) fits the engine's default
pool. More workers than the pool allows, or None, 0 or 1 (no limit in
llama-index-core), can fail with sqlalchemy.exc.TimeoutError. The sync
methods need an engine with a background event loop, such as one from
AlloyDBEngine.from_instance or AlloyDBEngine.afrom_instance.
AlloyDBEngine
A class for managing connections to a AlloyDB database.
Column
Column(name: 'str', data_type: 'str', nullable: 'bool' = True)
AlloyDBIndexStore
Index Store Table stored in an AlloyDB for PostgreSQL database.
BaseIndex
BaseIndex(name: Optional[str] = None, index_type: str = 'base', distance_strategy: llama_index_alloydb_pg.indexes.DistanceStrategy =
DistanceStrategy
Enumerator of the Distance strategies.
ExactNearestNeighbor
ExactNearestNeighbor(name: Optional[str] = None, index_type: str = 'exactnearestneighbor', distance_strategy: llama_index_alloydb_pg.indexes.DistanceStrategy =
HNSWIndex
HNSWIndex(name: Optional[str] = None, index_type: str = 'hnsw', distance_strategy: llama_index_alloydb_pg.indexes.DistanceStrategy =
HNSWQueryOptions
HNSWQueryOptions(ef_search: int = 40)
IVFFlatIndex
IVFFlatIndex(name: Optional[str] = None, index_type: str = 'ivfflat', distance_strategy: llama_index_alloydb_pg.indexes.DistanceStrategy =
IVFFlatQueryOptions
IVFFlatQueryOptions(probes: int = 1)
IVFIndex
IVFIndex(name: Optional[str] = None, index_type: str = 'ivf', distance_strategy: llama_index_alloydb_pg.indexes.DistanceStrategy =
IVFQueryOptions
IVFQueryOptions(probes: int = 1)
QueryOptions
API documentation for QueryOptions class.
ScaNNIndex
ScaNN index configuration for AlloyDB.
See https://cloud.google.com/alloydb/docs/ai/create-scann-index.
ScaNNQueryOptions
Query options for a ScaNN index.
See https://cloud.google.com/alloydb/docs/reference/ai/scann-index-reference.
StrategyMixin
API documentation for StrategyMixin class.
AlloyDBModel
A model endpoint registered in AlloyDB AI model endpoint management.
Fields use the create_model argument names, so asdict(model) without
model_id can be passed back to it. model_in_transform_fn,
model_out_transform_fn and generate_headers_fn are read from the
input_transform_fn, output_transform_fn and header_gen_fn view columns.
AlloyDBModelManager
Register, inspect and drop AlloyDB AI model endpoints.
See https://cloud.google.com/alloydb/docs/ai/register-model-endpoint.
AlloyDBRerank
Reranks nodes with AlloyDB AI's google_ml.rank() function.
The ranking runs inside the database through AlloyDB's Vertex AI
integration. As listed in
https://cloud.google.com/alloydb/docs/ai/rank-rerank-search-results-rag,
it needs the google_ml_integration extension 1.5.2 or later, the
google_ml_integration.enable_model_support and
google_ml_integration.enable_ai_query_engine flags on, the Discovery
Engine API enabled and roles/discoveryengine.viewer for the AlloyDB
service agent. Nodes with no text (an ImageNode) or only whitespace or
format characters are left out. Database errors are raised unchanged.
Async apostprocess_nodes needs llama-index-core 0.12.32 or later.
AlloyDBReader
Chat Store Table stored in an AlloyDB for PostgreSQL database.
AlloyDBToolSpec
Tools that run AlloyDB AI functions in the database.
AlloyDBToolSpec(engine).to_tool_list() returns one FunctionTool
per function, each with a native async path, ready for an agent such as
FunctionAgent. Requires AlloyDB for PostgreSQL 17 or later with the
google_ml_integration extension 1.5.7 or later and the
google_ml_integration.enable_ai_query_engine and
google_ml_integration.enable_preview_ai_functions flags on. See
https://cloud.google.com/alloydb/docs/ai/analyze-sentiment.
AlloyDBVectorStore
Google AlloyDB Vector Store class
Modules
chat_store
API documentation for chat_store module.
document_store
API documentation for document_store module.
embeddings
API documentation for embeddings module.
engine
API documentation for engine module.
index_store
API documentation for index_store module.
indexes
API documentation for indexes module.
model_manager
API documentation for model_manager module.
postprocessor
API documentation for postprocessor module.
reader
API documentation for reader module.
tools
API documentation for tools module.
vector_store
API documentation for vector_store module.