Skip to main content

​
Overview

LLM Retrieval is the process of making your data compatible with LLMs. This is done by embedding your data into a vector space, then indexed into a database. This allows you to run semantic searches on your data, which is the core of LLMs.

​
Use Cases

TitleDescriptionDemo
Semantic SearchLLMs give your search the knowledge of semantic meaningMulti Tenant search
ChatbotsUtilize LLMs to create chatbots that can answer questions on your dataRAG Chatbot
Question+AnsweringBuild Chat apps that answer questions on top of your unstructured dataChat App
Tabular AnalysisAnalyze tabular data with LLMsFinancial Analysis Chatbot
ClusteringUncover hidden trends within your unstructured dataClustering Tool
Image SearchSearch for images based on semantic meaningImage Retrieval with CLIP

​
Usage

​
Indexing

We provide APIs to easily push data into our system. We support the following “primitive” data types for ingestion:
  • Image URLs (.jpg, .png, .gif, .bmp, .tiff)
  • Text (string)
  • Embeddings (number[])
This data will then be pushed into our indexing pipeline to generate embeddings and store in a vector db. Checkout the Index endpoint for more details.

​
File Importing

We provide APIs to easily push larger collections of data into our system as well. We support the following file types for ingestion:
  • .csv
  • .docx
  • .pdf
  • .pptx
  • .txt
  • .xlsx
Upon upload, these files run through the following pipeline:
  1. The file runs through a series of metadata extractors + augmenters
  2. File is converted into a text representation via OCR (if applicable)
  3. The text is split into overlapping 500 token chunks
  4. These chunks are embedded based on the chosen embeddings model (ada, clip, etc)
  5. The embeddings are indexed into a Vector database
  6. Vector is indexed into our database

​
Searching

Run semantic search out of the box with our API. We support the following search term types:
  • Images (.jpg, .png, .gif, .bmp, .tiff)
  • Text (string)
  • Embeddings (number[])
Filtered search is also supported. Check out the Search endpoint for more details.

​
Definitions

TermDefinition
DocumentA record that stores an embedding & metadata
EmbeddingA vector representation of your data.
IndexA database of your embeddings.
IndexingPushing data (raw text, files, images, etc) into our system.
SearchAn operation to run semantic searches on your index.
TuningA mechanism to improve the quality of your embeddings for your particular use case.