-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'main' of https://github.com/data-max-hq/jinaai-demo
- Loading branch information
Showing
1 changed file
with
13 additions
and
5 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,19 +1,27 @@ | ||
# jinaai-demo | ||
# Open-Memory | ||
|
||
## Setup Guide | ||
* Clone the repository (data-max-hq/open-recall) | ||
* cd into /open-recall | ||
* Clone the repository (data-max-hq/open-memory) | ||
* cd into /open-memory | ||
* pip install pyautogui | ||
* In the terminal run ‘make build’ | ||
* In the terminal run ‘make run’ | ||
* After a couple of minutes then head over to "localhost:9876" | ||
* After a couple of minutes then head over to "localhost:8080" | ||
* In "ADD LLM" type out the LLM you want to use (we recomend qwen2:1.5b or qwen2:0.5b) and press "Add LLM" | ||
|
||
## Functionality | ||
Run "screenshot-desktop.py" to start capturin the screen | ||
|
||
|
||
Query ChromaDB: Test the database to retrieve relevant pieces of context for a specific query. | ||
|
||
|
||
LLM Prompt: Pass a query to QWEN2:1.5b to get an explanation of what the user was doing based on the retrieved context. | ||
Summary | ||
|
||
|
||
## Summary | ||
|
||
|
||
In summary, our open-source alternative to Windows Recall offers a secure, private, and efficient way to continuously record screens and perform OCR, ensuring that all data remains under the user's control. By leveraging the high-quality embedding and reranking models from JinaAI, we enhance the accuracy and relevance of the information retrieved, providing users with a powerful and privacy-conscious solution. This project demonstrates the potential of open-source tools to address privacy concerns while delivering robust functionality. | ||
|
||
|