The target-chromadb loader sends data into Chromadb after it was pulled from a source using an extractor
Getting Started
Prerequisites
If you haven't already, follow the initial steps of the Getting Started guide:
Installation and configuration
-
Add the target-chromadb loader to your
project using
:meltano add -
Configure the target-chromadb
settings using
:meltano config
meltano add loader target-chromadbmeltano config target-chromadb set --interactiveNext steps
Follow the remaining steps of the Getting Started guide:
If you run into any issues, learn how to get help.
Capabilities
The current capabilities for
target-chromadb
may have been automatically set when originally added to the Hub. Please review the
capabilities when using this loader. If you find they are out of date, please
consider updating them by making a pull request to the YAML file that defines the
capabilities for this loader.
This plugin has the following capabilities:
- about
- schema-flattening
- stream-maps
You can
override these capabilities or specify additional ones
in your meltano.yml by adding the capabilities key.
Settings
The
target-chromadb settings that are known to Meltano are documented below. To quickly
find the setting you're looking for, click on any setting name from the list:
Expand To Show SDK Settings
You can also list these settings using
with the meltano configlist
subcommand:
meltano config target-chromadb list
You can
override these settings or specify additional ones
in your meltano.yml by adding the settings key.
Please consider adding any settings you have defined locally to this definition on MeltanoHub by making a pull request to the YAML file that defines the settings for this plugin.
Collection Name (collection_name)
-
Environment variable:
TARGET_CHROMADB_COLLECTION_NAME -
Default Value:
vector-db
The Chroma collection name. Collections are where you'll store your embeddings, documents, and any additional metadata.
Configure this setting directly using the following Meltano command:
meltano config target-chromadb set collection_name [value]Database Directory (db_directory)
-
Environment variable:
TARGET_CHROMADB_DB_DIRECTORY -
Default Value:
output
The directory where Chroma will store its database files on disk, and load them on start.
Configure this setting directly using the following Meltano command:
meltano config target-chromadb set db_directory [value]Document Text Property (document_text_property)
-
Environment variable:
TARGET_CHROMADB_DOCUMENT_TEXT_PROPERTY -
Default Value:
page_content
The property containing the document text.
Configure this setting directly using the following Meltano command:
meltano config target-chromadb set document_text_property [value]Embeddings Property (embeddings_property)
-
Environment variable:
TARGET_CHROMADB_EMBEDDINGS_PROPERTY -
Default Value:
embeddings
The property containing the embeddings.
Configure this setting directly using the following Meltano command:
meltano config target-chromadb set embeddings_property [value]Metadata Property (metadata_property)
-
Environment variable:
TARGET_CHROMADB_METADATA_PROPERTY -
Default Value:
metadata
The property containing the document metadata.
Configure this setting directly using the following Meltano command:
meltano config target-chromadb set metadata_property [value]Expand To Show SDK Settings
Flattening Enabled (flattening_enabled)
-
Environment variable:
TARGET_CHROMADB_FLATTENING_ENABLED
'True' to enable schema flattening and automatically expand nested properties.
Configure this setting directly using the following Meltano command:
meltano config target-chromadb set flattening_enabled [value]Flattening Max Depth (flattening_max_depth)
-
Environment variable:
TARGET_CHROMADB_FLATTENING_MAX_DEPTH
The max depth to flatten schemas.
Configure this setting directly using the following Meltano command:
meltano config target-chromadb set flattening_max_depth [value]Stream Map Config (stream_map_config)
-
Environment variable:
TARGET_CHROMADB_STREAM_MAP_CONFIG
User-defined config values to be used within map expressions.
Configure this setting directly using the following Meltano command:
meltano config target-chromadb set stream_map_config [value]Stream Maps (stream_maps)
-
Environment variable:
TARGET_CHROMADB_STREAM_MAPS
Config object for stream maps capability. For more information check out Stream Maps.
Configure this setting directly using the following Meltano command:
meltano config target-chromadb set stream_maps [value]Something missing?
This page is generated from a YAML file that you can contribute changes to.
Edit it on GitHub!Looking for help?
#plugins-general-yellow){kind=icon}
-50-c0c0c4){kind=icon}
-9-c0c0c4){kind=icon}
