Vectorization Source

Vectorization Model Keep model in memory

The model must be downloaded first! Do it with the ollama pull command or click here.

Hint: Set the URL in the API connection settings.

The server MUST be started with the --embedding flag to use this feature! Hint: Set the URL in the API connection settings.

Vectorization Model

Vectorization Model Hint: Set the URL in the API connection settings.

NomicAI API Key

Click to set

Query messages

Score threshold

Chunk boundary

Include in World Info Scanning

World Info settings

Enable for World Info

Enabled for all entries

Checked: all entries except ❌ status can be activated.
Unchecked: only entries with 🔗 status can be activated.

Max Entries

File vectorization settings

Enable for files

Translate files into English before processing

Message attachments

Size threshold (KB)

Chunk size (chars)

Chunk overlap (%)

Retrieve chunks

Data Bank files

Size threshold (KB)

Chunk size (chars)

Chunk overlap (%)

Retrieve chunks

Injection Template Injection Position

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

Vectorize All

Purge Vectors

Chat vectorization settings

Enabled for chat messages

Injection Template Injection Position

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

Chunk size (chars)

Retain#

Insert#

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 or WebLLM Extension is selected.

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

Vectorize All

Purge Vectors

View Stats