Prevent model download when using delegated inference
[from Discord] The mobile app is trying to download models every time the app reloads. I need to re-toggle the delegation enabled button on every reload. It should enable delegate modes across reloads and restarts once I have set it up. And it should not try to always download models once delegation mode is setup.
QVAC | Product Team About 1 month ago
QVAC/ Workbench
Prevent model download when using delegated inference
[from Discord] The mobile app is trying to download models every time the app reloads. I need to re-toggle the delegation enabled button on every reload. It should enable delegate modes across reloads and restarts once I have set it up. And it should not try to always download models once delegation mode is setup.
QVAC | Product Team About 1 month ago
QVAC/ Workbench
Hello QVAC team. I'm on the waitlist for your SDK, and have a series of questions re: business alignments. Can we arrange a meeting with someone who can speak to both the business and technical aspects?
Heather Flannery About 2 months ago
Inquiries / Doubts
Hello QVAC team. I'm on the waitlist for your SDK, and have a series of questions re: business alignments. Can we arrange a meeting with someone who can speak to both the business and technical aspects?
Heather Flannery About 2 months ago
Inquiries / Doubts
Model-specific parameter limits with visual feedback
Prevent users from saving out-of-range parameters in their settings that cause model loading failures, requiring a full reset [with loss of conversations and settings]. What about: I. Dynamic limits per model [different safe ranges] II. Visual indicator [change slider color as values approach unsafe limits] III. Validation on "Save Settings" [warn if parameters may cause issues]
Sebastiano 2 months ago
QVAC/ Workbench
Model-specific parameter limits with visual feedback
Prevent users from saving out-of-range parameters in their settings that cause model loading failures, requiring a full reset [with loss of conversations and settings]. What about: I. Dynamic limits per model [different safe ranges] II. Visual indicator [change slider color as values approach unsafe limits] III. Validation on "Save Settings" [warn if parameters may cause issues]
Sebastiano 2 months ago
QVAC/ Workbench
Data Security Credentials
It would be a great idea to provide Official QVAC documentation that outlines all the security credentials that this product provides. I understand that, implicitly, the product is designed for privacy and security, but having an official document outlining all the security certificates that this product complies with would help for faster adoption by companies that require this type of documentation for Audit purposes.
Zlatko Zahirovic 2 months ago
Feature Requests
Data Security Credentials
It would be a great idea to provide Official QVAC documentation that outlines all the security credentials that this product provides. I understand that, implicitly, the product is designed for privacy and security, but having an official document outlining all the security certificates that this product complies with would help for faster adoption by companies that require this type of documentation for Audit purposes.
Zlatko Zahirovic 2 months ago
Feature Requests
Persistent memory and context
Without some persistent memory and context , unfortunately the dependence on other models remains very high. I am a data engineer and I can’t carry on a data project if I have to explain what we’re doing every time I ask a question. And I can’t get help with social-media writing either. Also the fact that always says “Hello” is a little bit annoying :) I think it would be great if Qvac’s strength were that it remembers my information, while keeping it private.
Tundra Parisi 2 months ago
Feature Requests
Persistent memory and context
Without some persistent memory and context , unfortunately the dependence on other models remains very high. I am a data engineer and I can’t carry on a data project if I have to explain what we’re doing every time I ask a question. And I can’t get help with social-media writing either. Also the fact that always says “Hello” is a little bit annoying :) I think it would be great if Qvac’s strength were that it remembers my information, while keeping it private.
Tundra Parisi 2 months ago
Feature Requests
Web Browser in the app
We are excited about the possabilities of the workbench for our project. Has anyone planned a browser capability to enable users to surf the web and extract inisghts from their browsing into their repo for local AI analysis?
Shawn Jensen 3 months ago
Inquiries / Doubts
Web Browser in the app
We are excited about the possabilities of the workbench for our project. Has anyone planned a browser capability to enable users to surf the web and extract inisghts from their browsing into their repo for local AI analysis?
Shawn Jensen 3 months ago
Inquiries / Doubts
Support custom model import also on Desktop version
[from keet] The desktop version should support the import of gguf models straight from the URL just like the mobile versions do
QVAC | Product Team 3 months ago
Prioritized
QVAC/ Workbench
Support custom model import also on Desktop version
[from keet] The desktop version should support the import of gguf models straight from the URL just like the mobile versions do
QVAC | Product Team 3 months ago
Prioritized
QVAC/ Workbench
Registry Files Not Cleaned Up on Uninstall - PC
It’s very interesting. Anyway, was messing around with the Delegated Inference to phone on PC and it mashed everything up. Had to Uninstall and Reinstall - but the lack of a clean uninstall is created file conflicts with the old registry entries, which probably should not be there anyway.
John Lillywhite 3 months ago
Feature Requests
Registry Files Not Cleaned Up on Uninstall - PC
It’s very interesting. Anyway, was messing around with the Delegated Inference to phone on PC and it mashed everything up. Had to Uninstall and Reinstall - but the lack of a clean uninstall is created file conflicts with the old registry entries, which probably should not be there anyway.
John Lillywhite 3 months ago
Feature Requests
Online learning llm
The flow llm generate text user does some updates or corrections corrected text is used as finetuning data Next time similar prompt appears, LLM uses learned patterns and user needs to make less corrections over time
Olya Sirkin 3 months ago
Feature Requests
Online learning llm
The flow llm generate text user does some updates or corrections corrected text is used as finetuning data Next time similar prompt appears, LLM uses learned patterns and user needs to make less corrections over time
Olya Sirkin 3 months ago
Feature Requests
Multi-thread memory
[extracted from the keet communityt room] Ensure all conversations/threads are embedded so that they are accessible via RAG from other threads, instead of isolated - like a kind of “memory”. Using memory or not could be optional per thread.
QVAC | Product Team 3 months ago
Harnessing feedback
QVAC/ Workbench
Multi-thread memory
[extracted from the keet communityt room] Ensure all conversations/threads are embedded so that they are accessible via RAG from other threads, instead of isolated - like a kind of “memory”. Using memory or not could be optional per thread.
QVAC | Product Team 3 months ago
Harnessing feedback
QVAC/ Workbench
Workbench support for Apple Intel
[retrieved from the Keet community] You should add support for Apple Intel to QVAC/Workbench
Hugo 3 months ago
Harnessing feedback
QVAC/ Workbench
Workbench support for Apple Intel
[retrieved from the Keet community] You should add support for Apple Intel to QVAC/Workbench
Hugo 3 months ago
Harnessing feedback
QVAC/ Workbench
Federated Learning for Image Generation
Derivated from https://qvacbytether.featurebase.app/p/local-image-generation Federated learning can definitely enhance the quality of diffusion models while offering a privacy-preserving alternative to centralized solutions. Unlike these solutions, where user data (prompts, generated images or seed uploads) is sent to servers for processing (and potentially retained), FL enables collaborative model training across decentralised devices without sharing raw data. It remains to be solved how good this can get, how scalable it is and what nodes have more incentive in handling this effort for the benefit of all. Universities could be an example.
QVAC | Product Team 3 months ago
Harnessing feedback
Feature Requests
Federated Learning for Image Generation
Derivated from https://qvacbytether.featurebase.app/p/local-image-generation Federated learning can definitely enhance the quality of diffusion models while offering a privacy-preserving alternative to centralized solutions. Unlike these solutions, where user data (prompts, generated images or seed uploads) is sent to servers for processing (and potentially retained), FL enables collaborative model training across decentralised devices without sharing raw data. It remains to be solved how good this can get, how scalable it is and what nodes have more incentive in handling this effort for the benefit of all. Universities could be an example.
QVAC | Product Team 3 months ago
Harnessing feedback
Feature Requests
Local Image Generation
Introducing a way for people to create images locally, easily and cross-platform seems really useful for any number of applications. Cloud services expose us to risks that something like this can eliminate: exposure: there are default public galleries and no opt-out for training on some providers, which means the images are shared and used to improve models. server retention: aside from caching upload (even sensitive ones) aside from promises that data is stored in segregated locations, “deleted” content is not clear and while its claimed to not be used for training, data retention policies change all the time. Without verification, the current policies basically equate to indefinite storage. costs: generating locally is not free (has some costs) but for scale (like design schools, etc.) it’s certainly cheaper Federated learning can complement this to ensure that the models keep improving for all - based on everyone’s information - but without all the implications above.
Hugo 3 months ago
Harnessing feedback
Feature Requests
Local Image Generation
Introducing a way for people to create images locally, easily and cross-platform seems really useful for any number of applications. Cloud services expose us to risks that something like this can eliminate: exposure: there are default public galleries and no opt-out for training on some providers, which means the images are shared and used to improve models. server retention: aside from caching upload (even sensitive ones) aside from promises that data is stored in segregated locations, “deleted” content is not clear and while its claimed to not be used for training, data retention policies change all the time. Without verification, the current policies basically equate to indefinite storage. costs: generating locally is not free (has some costs) but for scale (like design schools, etc.) it’s certainly cheaper Federated learning can complement this to ensure that the models keep improving for all - based on everyone’s information - but without all the implications above.
Hugo 3 months ago
Harnessing feedback
Feature Requests