CODEFIX: Made the intro text shorter, as it would overlat the history box.

CODEFIX: Add token counter, context management, and UI improvements

CODEFIX: Set 12k num_ctx. Introduced history. Added history counter.. Put input control at the bottom and made it fixed. Lowered temperature.

CODEFIX: Removed the clear chat button

CODEIFX: Try fix vector store retriever

CODEFIX: Try fix runtime problem in HF Space

CODEFIX: Added specific requirements.

CODEFIX: Added missing reference

Bug 20523: Web.Help: AI Chat stopped working. Changed to non-versioned requirements. Completely removed unused HF and Together references.

CODEFIX: Try to update langchain version to get this compiling on hf spaces

Bug 20523: Web.Help: AI Chat stopped working. Another try to get this working on HF Spaces

Update requirements.txt

Update requirements.txt

Update app.py

Update requirements.txt

Update requirements.txt

Update requirements.txt

Create .force-rebuild

Update requirements.txt

Bug 20523: Web.Help: AI Chat stopped working

Update requirements.txt

Update requirements.txt

Update requirements.txt

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

CODEFIX: Try to solve problem where HF has problems generating contents due to missing GPU access.

CODEFIX: Added Adrega styling to fonts and improved breaking after bulletpoints etc

CODEFIX: Made the text more readable by introducing markup

CODEFIX: Added adrega first and together last, because now we have our own fully working inference client

CODEFIX: Narrowed padding left and right to remove whitespace in Adrega chat

CODEFIX: Try to remove padding from main container in Streamlit to better fit inside Adrega AI Chat window.

CODEFIX: Removed HuggingFace as provider, as it always displayed thought process. Improved responces. Improved removal of thought process in general.

CODEFIX: Improved responses from Adrega and Hugging Face, to prevent them from revealing thought process.

CODEFIX: Improved the models to act in a more traditional chat way, instead of being in q&a mode.

CODEFIX: Added css file for style rule. Added 1 rule, to narrow the padding on the first control. Added memory for the model

CODEFIX: Set new Adrega model to Qwen3:1.7b, disapling the thinking specifically for all models. Made quesitons appear in grey

CODEFIX: Updated to use new json based context

CODEFIX: Try3 - Added langchain-openai library

CODEFIX: Try2 - Add langchain-huggingface specifically to requirements

CODEFIX: Try fix error with incorrect requirements.txt

CODEFIX: Implemented Together and Adrega as additional providers. Defaults to Together. Implemented langchain to split requests into chunks

CODEFIX: Try to remove unnecessary buttons. Removed huggingface_hub requirement. Implemented openai as alternative provider.

Update README.md

CODEFIX: Switched model and added more debug info to figure out why it doesn't work for embedded versions.

CODEFIX: Reordered models and added fallback due to problems with primary model changes