v7.2.1 - Mistral Badass

Release notes largely repeat the ones for v7.2.0 because this is a patch release...except for adding the new Mistral model.

Bug fix

Thanks to @NQDM-paul-sinclair for pointing out the single flipping missing comma, which caused v7.2.0 installation to fail!

Deprecation Notices

• The longstanding "instructor" embedding models have finally been superseded. They've been removed from the Models tab so you can no longer download them. Make sure to recreate any vector databases you've created with them because support will be removed in the next release.

Upgrade Instructions

For first time installation follow the github readme

INSTRUCTIONS FOR UPGRADING FROM A PRIOR VERSION

To upgrade from a prior version while still keeping your databases and models that were downloaded, perform the following steps:

• In your directory that contains all of the files currently...delete the Include, Lib, Scripts folders. (pertain to your virtual environment)
• Delete the pyvenv.cfg file. (pertains to your virtual environment)
• At this point, any and all files pertaining to your virtual environment are gone.
• Delete the Assets and CSS folders. (new ones will be provided in their entirety further below)
• Extract all the files from the .zip file for this release v7.2.1 and go into the src folder.
• Copy all files and folders EXCEPT THE CONFIG.YAML FILE into the aforementioned folder where you virtual environment USED TO BE. If there are any prompts indicating that files will be overwritten, CLICK YES since we're only updating necessary files now.
• EXCEPT THE CONFIG.YAML FILE!
• EXCEPT THE CONFIG.YAML FILE!
• last time...EXCEPT THE CONFIG.YAML FILE!

Afterwards, open a command prompt and run the installation instructions on this repository's page, namely:

python -m venv .

.\Scripts\activate

python setup_windows.py

Embedding Models.

Change	Details	Notes
Added	stella_en_400M_5	Superb lightweight model, arguably the best English-only small model.
Added	Alibaba-gte-modernbert-base	High context limit based on new "Modern Bert" architecture.

Chat Models

Change	Details	Notes
Added	Deepseek R1 - 7b	New introspective model.
Added	Deepseek R1 - 14b	New introspective model.
Added	Deepseek R1 - 32b	New introspective model.
Added	Mistral Small 3 - 24b	Outperforms 3x-sized models, plus permissive license.

Ask Jeeves!

• Jeeves can now talk!
  • Shout out to the people at Kokoro

• Updated Jeeves knowledge.
• Do not forget to set the proper permissions for the Kobold backend, as described in this repository's readme.

Metrics Bar

• Added an "arc" option. Right-click to change the visualization.
• In case you missed it, here are the current available options:

Bars

Sparkline

Speedometer

Arc (new)

Updated Dependencies

• Too many to mention...

v7.2.0 - Deepseek R1 arrives!

Deprecation Notices

• The longstanding "instructor" embedding models have finally been superseded. They've been removed from the Models tab so you can no longer download them. Make sure to recreate any vector databases you've created with them because support will be removed in the next release.

Upgrading

INSTRUCTIONS FOR UPGRADING FROM A PRIOR VERSION

To upgrade from a prior version while still keeping your databases and models that were downloaded, perform the following steps:

• In your directory that contains all of the files currently...delete the Include, Lib, Scripts folders. (pertain to your virtual environment)
• Delete the pyvenv.cfg file. (pertains to your virtual environment)
• At this point, any and all files pertaining to your virtual environment are gone.
• Delete the Assets and CSS folders. (new ones will be provided in their entirety further below)
• Extract all the files from the .zip file for this release v7.2.0 and go into the src folder.
• Copy all files and folders EXCEPT THE CONFIG.YAML FILE into the aforementioned folder where you virtual environment USED TO BE. If there are any prompts indicating that files will be overwritten, CLICK YES since we're only updating necessary files now.
• EXCEPT THE CONFIG.YAML FILE!
• EXCEPT THE CONFIG.YAML FILE!
• last time...EXCEPT THE CONFIG.YAML FILE!

Afterwards, open a command prompt and run the installation instructions on this repository's page, namely:

python -m venv .

.\Scripts\activate

python setup_windows.py

Embedding Models.

Change	Details	Notes
Added	stella_en_400M_5	Superb lightweight model, arguably the best English-only small model.
Added	Alibaba-gte-modernbert-base	High context limit based on new "Modern Bert" architecture.

Chat Models

Change	Details	Notes
Added	Deepseek R1 - 7b	New introspective model.
Added	Deepseek R1 - 14b	New introspective model.
Added	Deepseek R1 - 32b	New introspective model.

Ask Jeeves!

• Jeeves can now talk!
  • Shout out to the people at Kokoro

• Updated Jeeves knowledge.
• Do not forget to set the proper permissions for the Kobold backend, as described in this repository's readme.

Metrics Bar

• Added an "arc" option. Right-click to change the visualization.
• In case you missed it, here are the current available options:

Bars

Sparkline

Speedometer

Arc (new)

Updated Dependencies

• Too many to mention...

v7.1.0 - BEST embedding model

Deprecation Notices

• Vector databases created from this release forward will have a "dimensions" metadata attribute associated with them. This is in anticipation of future releases but should not be breaking as of now. If/when this becomes breaking, you'll need to re-create all your vector databases.

Upgrading

INSTRUCTIONS FOR UPGRADING FROM A PRIOR VERSION

To upgrade from a prior version while still keeping your databases and models that were downloaded, perform the following steps:

• In your directory that contains all of the files currently...delete the Include, Lib, Scripts folders. (pertain to your virtual environment)
• Delete the pyvenv.cfg file. (pertains to your virtual environment)
• At this point, any and all files pertaining to your virtual environment are gone.
• Delete the Assets and CSS folders. (new ones will be provided in their entirety further below)
• Extract all the files from the .zip file for this release v7.1.0 and go into the src folder.
• Copy all files and folders EXCEPT THE CONFIG.YAML FILE into the aforementioned folder where you virtual environment USED TO BE. If there are any prompts indicating that files will be overwritten, CLICK YES since we're only updating necessary files now.
• EXCEPT THE CONFIG.YAML FILE!
• EXCEPT THE CONFIG.YAML FILE!
• last time...EXCEPT THE CONFIG.YAML FILE!

Afterwards, open a command prompt and run the installation instructions on this repository's page, namely:

python -m venv .

.\Scripts\activate

python setup_windows.py

Python 3.11 and Python 3.12 support

The new consolidated setup_windows.py script will automatically choose the appropriate dependencies based on your Python version. you no longer need to choose between the two installation scripts.

Bug Fixes

• Not many this time around.

Embedding Models.

Change	Details	Notes
Added	stella_en_1.5B_v5	Arguably the highest quality embedding model in this program now.
Added	static-retrieval-mrl-en-v1	The new fastest model this program offers. Experimental, use with caution. I am working on getting the parameters set correctly.

Chat Models

Change	Details	Notes
Added	InternLM 3 - 8b	Claims to beat Qwen2.5 and is great for RAG.

Ask Jeeves!

• General improvements to make it load and function more smoothly. Do not forget to set the proper permissions as described in this repository's readme.
• Updated Jeeves knowledge.

Documentation Scraper

• Updated libraries yet again so the scraped .html files are more pristine.

Updated Dependencies

• Too many to mention...

General

• Added new Nvidia and Intel GPUs to the GPU chart.

v7.0.0 - HAPPY NEW YEAR!

Breaking Changes

• Only EVERYTHING.

Upgrading

To upgrade from a prior version while still keeping your databases and models that were downloaded, perform the following steps:

• In your directory that contains all of the files currently...delete the Include, Lib, Scripts folders. (pertain to your virtual environment)
• Delete the pyvenv.cfg file. (pertains to your virtual environment)
• At this point, any and all files pertaining to your virtual environment are gone.
• Delete the Assets and CSS folders. (new ones will be provided in their entirety further below)
• Extract all the files from the .zip file for this release v7.0.0 and go into the src folder.
• Copy all files and folders EXCEPT THE CONFIG.YAML FILE into the aforementioned folder where you virtual environment USED TO BE. If there are any prompts indicating that files will be overwritten, CLICK YES since we're only updating necessary files now.
• EXCEPT THE CONFIG.YAML FILE!
• EXCEPT THE CONFIG.YAML FILE!
• last time...EXCEPT THE CONFIG.YAML FILE!

Afterwards, open a command prompt and run the installation instructions on this repository's page, namely:

1. Open a command prompt in the directory and run:
   python -m venv . and .\Scripts\activate
2. Then based on your Python version (we now support Python 3.11 and 3.12) run:
   python setup_windows_cp311.py or python setup_windows_cp312.py

Python 3.11 and Python 3.12 support

• Just make sure and run the proper installation scripts.

Bug Fixes

• Too many to list.

Embedding Models.

Change	Details	Notes
Added	granite - 30m and granite - 125m	All are excellent for RAG
Added	arctic-embed-m and arctic-embed-l	Also excellent for RAG
Removed	all-MiniLM-L12-v2, all-mpnet-base-v2, gte-small, gte-base, and gte-large	All superseded by either granite or arctic-embed models.

Chat Models

Change	Details	Notes
Added	granite - 2b and granite - 8b	All seem to be destined for RAG
Added	exaone - 2.4b, exaone - 7.8b, and exaone - 32b	Great for RAG
Removed	Qwen - 3b, Llama 3.2 - 3b, Phi 3.5 Mini - 4b, MiniCPM3 - 4b, Qwen - 7b, Dolphin-Llama 3.1 - 8b, Marco-o1 - 7b	All superseded in quality, speed, or both.

Vision Models

Change	Details	Notes
Added	InternVL 2.5 - 1b and InternVL 2.5 - 4b	Very good with low resources even
Removed	Llava 1.6 - Vicuna and MiniCPM 2.6 - 8b	Beaten by InternVL 2.5 models.

Ask Jeeves!

• When Jeeves first loads you now have the ability to choose his "brain," which can be any of the following GGUF models:
  • EXAONE - 2.4b Q8_0, EXAONE - 7.8b Q4_K_M, Llama 3.2 Q8_0, Qwen - 3b Q8_0 or Zephyr - 3b Q8_0
• Three suggested queries are populated as you type. Click to automatically ask Jeeves that specific question.
• Darker color theme.

Documentation Scraper

• Updated libraries to scrape and the .html file created is more pristine - i.e. less sidebars, menus, etc. - you should now get higher quality .html files, which, in turn, allows for higher quality vector database searches.
• More scraping optimizations to come since there are so many libraries to customize the scraper for.

Updated Dependencies

• torch 2.5.1 is now used, which finally allows this program to be compatible with Python 3.12.
• CUDA, triton, bitsandbytes, flash attention 2, langchain, and a ton of other dependencies updated.

There are a host of other improvements but this is long enough!

v6.11.0 - bug fixes

Added/Removed Embedding Models

• Added sentence-t5-xxl
  • Massive model specifically geared towards finding sentences as close as possible to the sentence you pose in your query.

Documentation Scraper

• Better colors.

Bug Fixes

• Fixed a huge bug with chat models that prevented them from working at all.
• Fixed all sentence-t5 models from using way too much memory.

Misc.

• Improved the "chunks only" functionality and memory management in general.
• Improved the layout of "chunks" returned when "chunks only" is selected.
• Upgraded lots of dependencies.
• Adjusted batch sizes for embedding models.

Upgrading from v6.9.x (will not work with prior versions):

To upgrade from a prior version without losing your databases, downloaded models, etc., do the following:

• Download the source code for this release.
• Take all files ending in .py and copy them, overwriting your pre-existing files. MAKE SURE and keep your current config.yaml.
• Copy any files in the Assets folder and replace any ones in your current Assets folder.
• Do the same for any files in the CSS folder.
• Activate your virtual environment and run the following command to uninstall any & all dependencies.
  • pip freeze > requirements_uninstall.txt && pip uninstall -r requirements_uninstall.txt -y && del requirements_uninstall.txt
  • run python setup_windows.py

v6.10.1 - Ovis & Mississippi

Added/Removed Vision Models

• Added Mississippi - 2b
  • This is an exciting new vision model that's 95% the quality of the larger models at 3-4x the speed.
  • Relies on the InternViT-300M-448px vision tower.
• Added Ovis 1.6 Llama3.2 - 3b model
  • Another high quality model that's faster than the larger models with arguably the same quality.
  • Relies on the siglip-so400m-patch14-384 vision tower.

Documentation Scraper

• Now using watchdog for more accurate updates on the number of pages scraped.

Misc.

• Started using the great ruff library to fix my code.

Upgrading from v6.9.x (will not work with prior versions):

To upgrade from a prior version without losing your databases, downloaded models, etc., do the following:

• Download the source code for this release.
• Take all files ending in .py and copy them, overwriting your pre-existing files. MAKE SURE and keep your current config.yaml.
• Copy any files in the Assets folder and replace any ones in your current Assets folder.
• Do the same for any files in the CSS folder.
• Activate your virtual environment and run the following command to uninstall any & all dependencies.
  • pip freeze > requirements_uninstall.txt && pip uninstall -r requirements_uninstall.txt -y && del requirements_uninstall.txt
  • run python setup_windows.py

v6.10.0 - So much time wasted!

Upgrading from v6.9.x

To upgrade from a prior version without losing your databases, downloaded models, etc., do the following:

• Download the source code for this release.
• Take all files ending in .py and copy them, overwriting your pre-existing files. MAKE SURE and keep your current config.yaml.
• Copy any files in the Assets folder and replace any ones in your current Assets folder.
• Do the same for any files in the CSS folder.
• Activate your virtual environment and run the following command to uninstall any & all dependencies.
  • pip freeze > requirements_uninstall.txt && pip uninstall -r requirements_uninstall.txt -y && del requirements_uninstall.txt
  • run python setup_windows.py

Added/Removed Chat Models

• Added Marco-o1 - 7b
  • This is a superb model that performs chain-of-thought. It is slower than other models (thinking behind the scenes), but produces extremely accurate results even with long contexts.
• Added Qwen 2.5 Coder - 3b
• Added Qwen 2.5 Coder - 14b
• Added Qwen 2.5 - 32b
• Added Qwen 2.5 Coder - 32b
• Removed Internlm2_5 - 1.8b
• Removed Yi Coder - 9b
• Removed Internlm2_5 - 7b
• Removed DeepSeek Coder v2 - 16b
  • Eclipsed by the better and faster Qwen 2.5 Coder - 14b model.
• Removed Internlm2_5 - 20b
  • Eclipsed by Qwen 2.5 - 14b and/or Qwen 2.5 32b

Added/Removed Vision Models

• Added THUDM glm4v - 9b
• Added Molmo-D-0924 - 8b

Scrape Python Library Documentation

• Added multiple new libraries and newer versions of existing libraries to scrape.
• Improved .html formatting of scraped cites to feed the vector database more relevant information.
• Increased the speed and reliability of scraping documentation by using lxml within beautifulsoup4 and other alternations.
• Created module_scraper.py to handle scraping logic while gui_tabs_tools_scrape.py still provides the GUI.

Ask Jeeves Improvements

• Added more error handling and server connection indicators as well as better subprocess handling.

Other Improvements

• Updated dependencies.
• Refactored document_processor.py to accommodate newer dependencies and load .html file faster.
• Additional file filters to reduce download amounts when downloading models.
• Added a button to display vision model bar charts.

v6.9.2 - Welcome Kobold!

Patch 6.9.2 Notes

In between major updates I'll simply paste below the major update notes so it's more convenient, and then include specific notes for minor updates.

• Added MiniCPM3 - 4b chat model
  • Very very good at at single factoid retrieval, even from many contexts, but DO NOT use when asking to retrieve multiple factoids from the contexts because it will ramble.
• Robust validation of settings entered.
• Use qthread with metrics bar for smoother GUI operation
• Add page numbers when contexts that originate from a .pdf are returned.
• Return relevant scores for all citations, which helps users determine which similarity setting to use.

Patch 6.9.1 Notes

• Added Qwen 2.5 - 32b chat model.
• Add sparkgraphs for metrics and the ability to right-click on the metrics bar and select a different visualization.

Welcome Kobold edition v6.9.0

Ask Jeeves!

• Exciting new "Ask Jeeves" helper who answers questions about how to use the program. Simply click "Jeeves" in the upper left.
• "Jeeves" gets his knowledge from a vector database that comes shipped with this release! NO MORE USER GUIDE TAB - just ASK JEEVES!
  • IMPORTANT: After running setup_windows.py you must go into the Assets folder, right-click on koboldcpp_nocuda.exe, and check the "Unblock" checkbox first! If it's not there, try starting Jeeves and see if it works. Create a Github Issue if it doesn't work because Ask Jeeves is a new feature.
  • IMPORTANT: You may also need to disable or make an exception for any firewall you have. Submit a Github Issue if you encounter any problems.

Scrape Python Library Documentation

• In the Tools Tab, simply select a python library, click Scrape, and all the .html files will be downloaded to the Scraped_Documentation folder.
• Create a vector database out of all of the .html files for a given library, then use one of the coding specific models to answer questions!

Huggingface Access Token

• You can now enter an "access token" and access models that are "gated" on huggingface. Currently, llama 3.2 - 3b and mistral-small - 22b are the only gated models.
• Ask Jeeves how to get a huggingface access token.

Other Improvements

• The vector models are now downloaded using the snapshot_download functionality from huggingface_hub, which can exclude unnecessary files such as onnx, .bin (when an equivalent .safetensors version is available), and others. This significantly reduces the amount of data that this program downloads and therefore increases speed and usability.
• This speedup should pertain to vector, chat, and whisper models, and implementing the snapshot_download for TTS models is planned.
• New Compare GPUs button in the Tools Tab, which displays metrics for various GPUs so you can better determine your settings. Charts and graphs for chat/vision models will be added in the near future.
• New metrics bar with speedometer-looking widgets.
• Removed the User Guide Tab altogether to free up space. You can now simply Ask Jeeves instead.
• Lots and lots of refactoring to improve various things...

Added/Removed Chat Models

• Added Qwen 2.5 - 1.5b, Llama 3.2 - 3b, Internlm 2.5 - 1.8b, Dolphin-Llama 3.1 - 8b, Mistral-Small - 22b.
• Removed Longwriter Llama 3.1 - 8b, Longwriter GLM4 - 9b, Yi - 9b, Solar Pro Preview - 22.1b.

Added/Removed Vision Models

• Removed Llava 1.5, Bakllava, Falcon-vlm - 11b, and Phi-3-Vision models as either under-performing or eclipsed by pre-existing models that have additional benefits.

Roadmap

• Add Kobold as a backend in addition to LM Studio and Local Models, at which point I'll probably have to rename this github repo.
• Add OpenAI backend.
• Remove LM Studio Server settings and revise instructions since LM Studio has changed significantly since they were last done.

Full Changelog: v6.8.2...v6.9.0

v6.9.1 - Welcome Kobold!

Patch 6.9.1 Notes

In between major updates I'll simply paste below the major update notes so it's more convenient, and then include specific notes for minor updates.

• Added Qwen 2.5 - 32b chat model.
• Add sparkgraphs for metrics and the ability to right-click on the metrics bar and select a different visualization.

Welcome Kobold edition v6.9.0

Ask Jeeves!

• Exciting new "Ask Jeeves" helper who answers questions about how to use the program. Simply click "Jeeves" in the upper left.
• "Jeeves" gets his knowledge from a vector database that comes shipped with this release! NO MORE USER GUIDE TAB - just ASK JEEVES!
  • IMPORTANT: After running setup_windows.py you must go into the Assets folder, right-click on koboldcpp_nocuda.exe, and check the "Unblock" checkbox first! If it's not there, try starting Jeeves and see if it works. Create a Github Issue if it doesn't work because Ask Jeeves is a new feature.
  • IMPORTANT: You may also need to disable or make an exception for any firewall you have. Submit a Github Issue if you encounter any problems.

Scrape Python Library Documentation

• In the Tools Tab, simply select a python library, click Scrape, and all the .html files will be downloaded to the Scraped_Documentation folder.
• Create a vector database out of all of the .html files for a given library, then use one of the coding specific models to answer questions!

Huggingface Access Token

• You can now enter an "access token" and access models that are "gated" on huggingface. Currently, llama 3.2 - 3b and mistral-small - 22b are the only gated models.
• Ask Jeeves how to get a huggingface access token.

Other Improvements

• The vector models are now downloaded using the snapshot_download functionality from huggingface_hub, which can exclude unnecessary files such as onnx, .bin (when an equivalent .safetensors version is available), and others. This significantly reduces the amount of data that this program downloads and therefore increases speed and usability.
• This speedup should pertain to vector, chat, and whisper models, and implementing the snapshot_download for TTS models is planned.
• New Compare GPUs button in the Tools Tab, which displays metrics for various GPUs so you can better determine your settings. Charts and graphs for chat/vision models will be added in the near future.
• New metrics bar with speedometer-looking widgets.
• Removed the User Guide Tab altogether to free up space. You can now simply Ask Jeeves instead.
• Lots and lots of refactoring to improve various things...

Added/Removed Chat Models

• Added Qwen 2.5 - 1.5b, Llama 3.2 - 3b, Internlm 2.5 - 1.8b, Dolphin-Llama 3.1 - 8b, Mistral-Small - 22b.
• Removed Longwriter Llama 3.1 - 8b, Longwriter GLM4 - 9b, Yi - 9b, Solar Pro Preview - 22.1b.

Added/Removed Vision Models

• Removed Llava 1.5, Bakllava, Falcon-vlm - 11b, and Phi-3-Vision models as either under-performing or eclipsed by pre-existing models that have additional benefits.

Roadmap

• Add Kobold as a backend in addition to LM Studio and Local Models, at which point I'll probably have to rename this github repo.
• Add OpenAI backend.
• Remove LM Studio Server settings and revise instructions since LM Studio has changed significantly since they were last done.

Full Changelog: v6.8.2...v6.9.0

v6.9.0 - Welcome Kobold!!

Welcome Kobold edition

Ask Jeeves!

• Exciting new "Ask Jeeves" helper who answers questions about how to use the program. Simply click "Jeeves" in the upper left.
• "Jeeves" gets his knowledge from a vector database that comes shipped with this release! NO MORE USER GUIDE TAB - just ASK JEEVES!
  • IMPORTANT: After running setup_windows.py you must go into the Assets folder, right-click on koboldcpp_nocuda.exe, and check the "Unblock" checkbox first! If it's not there, try starting Jeeves and see if it works. Create a Github Issue if it doesn't work because Ask Jeeves is a new feature.
  • IMPORTANT: You may also need to disable or make an exception for any firewall you have. Submit a Github Issue if you encounter any problems.

Scrape Python Library Documentation

• In the Tools Tab, simply select a python library, click Scrape, and all the .html files will be downloaded to the Scraped_Documentation folder.
• Create a vector database out of all of the .html files for a given library, then use one of the coding specific models to answer questions!

Huggingface Access Token

• You can now enter an "access token" and access models that are "gated" on huggingface. Currently, llama 3.2 - 3b and mistral-small - 22b are the only gated models.
• Ask Jeeves how to get a huggingface access token.

Other Improvements

• The vector models are now downloaded using the snapshot_download functionality from huggingface_hub, which can exclude unnecessary files such as onnx, .bin (when an equivalent .safetensors version is available), and others. This significantly reduces the amount of data that this program downloads and therefore increases speed and usability.
• This speedup should pertain to vector, chat, and whisper models, and implementing the snapshot_download for TTS models is planned.
• New Compare GPUs button in the Tools Tab, which displays metrics for various GPUs so you can better determine your settings. Charts and graphs for chat/vision models will be added in the near future.
• New metrics bar with speedometer-looking widgets.
• Removed the User Guide Tab altogether to free up space. You can now simply Ask Jeeves instead.
• Lots and lots of refactoring to improve various things...

Added/Removed Chat Models

• Added Qwen 2.5 - 1.5b, Llama 3.2 - 3b, Internlm 2.5 - 1.8b, Dolphin-Llama 3.1 - 8b, Mistral-Small - 22b.
• Removed Longwriter Llama 3.1 - 8b, Longwriter GLM4 - 9b, Yi - 9b, Solar Pro Preview - 22.1b.

Added/Removed Vision Models

• Removed Llava 1.5, Bakllava, Falcon-vlm - 11b, and Phi-3-Vision models as either under-performing or eclipsed by pre-existing models that have additional benefits.

Roadmap

• Add Kobold as a backend in addition to LM Studio and Local Models, at which point I'll probably have to rename this github repo.
• Add OpenAI backend.
• Remove LM Studio Server settings and revise instructions since LM Studio has changed significantly since they were last done.

Full Changelog: v6.8.2...v6.9.0