Vectorization Source

Vectorization Model

It is recommended to purge vectors when changing the model mid-chat. Otherwise, it will lead to sub-par results.

NomicAI API Key

For privacy reasons, your API key will be hidden after you reload the page.

Query messages

Include in World Info Scanning

File vectorization settings

Enabled for files

Size threshold (KB)

Chunk size (chars)

Retrieve chunks

Chat vectorization settings

Enabled for chat messages

Vector Summarization

Summarize chat messages for vector generation Warning: This will slow down vector generation drastically, as all messages have to be summarized first. Summarize chat messages when sending Warning: This might cause your sent messages to take a bit to process and slow down response time. Summarize with: Summary Prompt: Only used when Main API is selected.

Insertion Template Injection Position

Before Main Prompt / Story String After Main Prompt / Story String In-chat @ Depth

Chunk size (chars)

Retain#

Insert#

Old messages are vectorized gradually as you chat. To process all previous messages, click the button below.

Vectorize All

Purge Vectors

View Stats