{"id":112185,"date":"2023-12-13T15:10:23","date_gmt":"2023-12-13T13:10:23","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/mozilla-predstavila-vstraivaemyj-v-brauzer-ai-bot-memorycache"},"modified":"2023-12-13T15:10:23","modified_gmt":"2023-12-13T13:10:23","slug":"mozilla-predstavila-vstraivaemyj-v-brauzer-ai-bot-memorycache","status":"publish","type":"post","link":"https:\/\/prohoster.info\/en\/blog\/news\/mozilla-predstavila-vstraivaemyj-v-brauzer-ai-bot-memorycache","title":{"rendered":"Mozilla has introduced the browser-integrated AI bot MemoryCache","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"
Mozilla has released an experimental add-on, MemoryCache, featuring a machine learning dialogue system that takes into account the content users access in their browser. Unlike other AI chats, MemoryCache allows for personalized interaction with the user and utilizes data relevant to the specific user when generating responses to inquiries. The project code is distributed under the MPL license. Currently, installation in Firefox is only supported manually via 'about:debugging' and requires the application of a patch. <\/p>\n
All components of MemoryCache run on the user's system without accessing external resources. The knowledge base of MemoryCache utilizes the GPT4All-J model, trained on collections of English language content such as Pile (825 GB of data), ShareGPT (13 MB), and Dolly (660 MB), and is available in versions with 3, 7, and 13 billion parameters. The privateGPT toolkit is used for working with the model, optimized for utilizing large language models on local machines. <\/p>\n
The Memory Cache add-on saves viewed pages in the directory '~\/Downloads\/MemoryCache', from which a periodically run script retrieves them and sends them to the privateGPT handler (ingest.py) to enhance the existing language model. This way, the model adapts to the user's interests and can be used for discussing the viewed content in a text chat with the bot. Users can ask the bot questions about the saved pages in natural language, for example, to clarify certain facts, and the bot will generate a response using the local model without resorting to external services. \n Source: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"