JavaScript SDK
Last updated
Last updated
Mindplug is the easiest solution to creating and managing embeddings. Add long term memory to your LLMs, perform semantic data analysis and easily filter data based on metadata. Connect your app to external web sources using our smart endpoint.
NPM:
yarn:
Obtain an API key from dashboard.
If you don't yet have access, please .
All storage of data requires a db and a collection.
Store text. Requires content
Store PDF file. Requires an object of type File under 50MB
Store webpage. Requires the webpage url
Store audio. Requires a MP3 or WAV file under 20MB
Storing - Advanced Techniques
A metadata
of type JSON and a chunkSize
of type number may also be passed to each storage function. Metadata is used to easily filter for data. Chunk size is used to split large data into smaller batches. By default the data is split in about 1024 character chunks.
Semantic search. Search stored data by meaning of text.
Query by vector ids.
Query by collection. Returns the recent 10 vectors from the collection.
Query - Advanced Techniques
By default, mindplug returns the 3 best matches for the searched data. You can change this by passing a count
parameter. You can also filter the stored data based on metadata by passing in a metadataFilters
parameter.
Delete by vector ids.
Delete by upload id. Upload id is returned every time new data is stored
Delete collection. Also deletes all vectors stored within.
Delete project. Also deletes all collections and vectors stored within.
List Collections.
List projects.
Google search from select sources.
You can easily manage all your data in the Mindplug dashboard.
Get all text from a webpage given its URL.
Returns all text on the webpage.
For more information on using metadataFilters, please see our API