Version upped

updated models info

Fix API errors for unknown models and compressed responses

Set sensible default outputTokens for unknown models (8k general,
32k for Anthropic) to avoid max_tokens=0 API errors. Disable
Accept-Encod

Fix API errors for unknown models and compressed responses

Set sensible default outputTokens for unknown models (8k general,
32k for Anthropic) to avoid max_tokens=0 API errors. Disable
Accept-Encoding to prevent unhandled brotli-compressed responses
from Cloudflare.

show more ...

Version upped

Fix chunksize calculation

Version upped

make fullpagecontext a numeric setting

You now can define how many pages should be sent, regardless of the
number of matching chunks.
Pages are still identified via the chunks, so this number can't

make fullpagecontext a numeric setting

You now can define how many pages should be sent, regardless of the
number of matching chunks.
Pages are still identified via the chunks, so this number can't be
larger than the chunks.

show more ...

Version upped

Update Gemini model configurations

Updated model configurations to include new Gemini versions and removed outdated ones.

Version upped

avoid deleting non-existant chunks. fixes #46

Version upped

fix interface handling with generic model

Version upped

make ollama auth optional

fix double intro message. fixes #44

connectedCallback may run multiple times, because the component is
readded to the dom when the section edit initializes.

Version upped

upped version

add tests for text splitting

make overlap a class member for easier testing

Agents: make clearer how to run tests

added an AGENTS.md file for LLM based work

split sentences by token, not bytes. handle UTF-8

move text splitting into it's own class

Some enhancements on the subsentence splitting

When a sentence is longer than a chunk, it should be split forcefully in
smaller parts - these parts should NOT be the size of a full chunk since
we st

Some enhancements on the subsentence splitting

When a sentence is longer than a chunk, it should be split forcefully in
smaller parts - these parts should NOT be the size of a full chunk since
we still want to do some overlap with previous and following texts. I
chose to split into a quarter of a chunk.

This also ensures that whitespace is kept for the split sentences,
because they may be joined with follow up texts.

show more ...