Storage

Vector Stores

Vectorstores

PrivateGPT supports Qdrant, Chroma and PGVector as vectorstore providers. Qdrant being the default.

In order to select one or the other, set the vectorstore.database property in the settings.yaml file to qdrant, chroma or postgres.

1vectorstore:
2  database: qdrant

Qdrant configuration

To enable Qdrant, set the vectorstore.database property in the settings.yaml file to qdrant.

Qdrant settings can be configured by setting values to the qdrant property in the settings.yaml file.

The available configuration options are:

FieldDescription
locationIf :memory: - use in-memory Qdrant instance. If str - use it as a url parameter.
urlEither host or str of ‘Optional[scheme], host, Optional[port], Optional[prefix]‘. Eg. http://localhost:6333
portPort of the REST API interface. Default: 6333
grpc_portPort of the gRPC interface. Default: 6334
prefer_grpcIf true - use gRPC interface whenever possible in custom methods.
httpsIf true - use HTTPS(SSL) protocol.
api_keyAPI key for authentication in Qdrant Cloud.
prefixIf set, add prefix to the REST URL path. Example: service/v1 will result in http://localhost:6333/service/v1/{qdrant-endpoint} for REST API.
timeoutTimeout for REST and gRPC API requests. Default: 5.0 seconds for REST and unlimited for gRPC
hostHost name of Qdrant service. If url and host are not set, defaults to ‘localhost’.
pathPersistence path for QdrantLocal. Eg. local_data/private_gpt/qdrant
force_disable_check_same_threadForce disable check_same_thread for QdrantLocal sqlite connection, defaults to True.

By default Qdrant tries to connect to an instance of Qdrant server at http://localhost:3000.

To obtain a local setup (disk-based database) without running a Qdrant server, configure the qdrant.path value in settings.yaml:

1qdrant:
2  path: local_data/private_gpt/qdrant

Chroma configuration

To enable Chroma, set the vectorstore.database property in the settings.yaml file to chroma and install the chroma extra.

$poetry install --extras chroma

By default chroma will use a disk-based database stored in local_data_path / “chroma_db” (being local_data_path defined in settings.yaml)

PGVector

To use the PGVector store a postgreSQL database with the PGVector extension must be used.

To enable PGVector, set the vectorstore.database property in the settings.yaml file to postgres and install the vector-stores-postgres extra.

$poetry install --extras vector-stores-postgres

PGVector settings can be configured by setting values to the postgres property in the settings.yaml file.

The available configuration options are:

FieldDescription
hostThe server hosting the Postgres database. Default is localhost
portThe port on which the Postgres database is accessible. Default is 5432
databaseThe specific database to connect to. Default is postgres
userThe username for database access. Default is postgres
passwordThe password for database access. (Required)
schema_nameThe database schema to use. Default is private_gpt

For example:

1vectorstore:
2  database: postgres
3
4postgres:
5  host: localhost
6  port: 5432
7  database: postgres
8  user: postgres
9  password: <PASSWORD>
10  schema_name: private_gpt

The following table will be created in the database

postgres=# \d private_gpt.data_embeddings
                                      Table "private_gpt.data_embeddings"
  Column   |       Type        | Collation | Nullable |                         Default
-----------+-------------------+-----------+----------+---------------------------------------------------------
 id        | bigint            |           | not null | nextval('private_gpt.data_embeddings_id_seq'::regclass)
 text      | character varying |           | not null |
 metadata_ | json              |           |          |
 node_id   | character varying |           |          |
 embedding | vector(768)       |           |          |
Indexes:
    "data_embeddings_pkey" PRIMARY KEY, btree (id)
postgres=#

The dimensions of the embeddings columns will be set based on the embedding.embed_dim value. If the embedding model changes this table may need to be dropped and recreated to avoid a dimension mismatch.

Built with