Update README.md
This commit is contained in:
parent
32edf2e5eb
commit
9b94a76121
1 changed files with 46 additions and 12 deletions
58
README.md
58
README.md
|
@ -1,21 +1,55 @@
|
||||||
pdf ai but free and open-source
|
Chat locally with any PDF
|
||||||
work in progress
|
|
||||||
|
|
||||||
early test :
|
Ask questions, get answer with usefull references
|
||||||
|
|
||||||
|
Work well with math pdfs (convert them to LaTex, a math syntax comprehensible by computer)
|
||||||
|
|
||||||
|
## Work flow chart
|
||||||
|
|
||||||
|

|
||||||
|
|
||||||
|
|
||||||
|
## Demos
|
||||||
|
|
||||||
|
chatbot test with some US Laws pdf
|
||||||
|
|
||||||
|
https://github.com/Crizomb/ai_pdf/assets/62544756/b399d5bc-df2f-4be0-b6fe-0c272f915c72
|
||||||
|
|
||||||
|
chatbot test with math pdf (interpereted as latex by the LLM)
|
||||||
|
|
||||||
|
https://github.com/Crizomb/ai_pdf/assets/62544756/eebf5520-bf78-4b82-8699-782e6d7147c4
|
||||||
|
|
||||||
|
full length process of converting pdf to latex, then using the chat bot
|
||||||
|
|
||||||
|
https://github.com/Crizomb/ai_pdf/assets/62544756/57bcc035-a7e0-4fdb-8c3a-4e72152765fa
|
||||||
|
|
||||||
|
## How to use
|
||||||
|
|
||||||
|
Clone the project to some location that we will call 'x'
|
||||||
|
|
||||||
|
Put your pdfs in x/ai_pdf/documents/pdfs
|
||||||
|
Run x/ai_pdf/main.py
|
||||||
|
Select or not math mode
|
||||||
|
Choose the pdf you want to work on
|
||||||
|
Wait a little bit for the pdf to get vectorized (check task manager to see if your gpu is going vrum)
|
||||||
|
|
||||||
|
Launch LM Studio, Go to the local Server tab, choose 1234 as server port, start server
|
||||||
|
(If you want to use open-ai or any other cloud LLM services, change line 10 of x/ai_pdf/back_end/inference.py with your api_key and your provider url)
|
||||||
|
|
||||||
|
Ask questions to the chatbot
|
||||||
|
Get answer
|
||||||
|
Go eat cookies
|
||||||
|
|
||||||
https://github.com/Crizomb/ai_pdf/assets/62544756/c7d71cc5-a18a-460c-a39c-63953e6e6a10
|
|
||||||
|
|
||||||
### TODO
|
### TODO
|
||||||
|
|
||||||
- [ ] Option tabs
|
- [ ] Option tabs
|
||||||
- [ ] menu to select different embedding models, add default chunk size for each models
|
- [ ] add more different embedding models
|
||||||
- [ ] menu to select pytorch acceleration (cuda etc...)
|
- [ ] menu to configure api url and api key
|
||||||
- [ ] menu to change api client
|
|
||||||
|
## Maybe in the futur
|
||||||
- [X] LaTex support
|
|
||||||
- [X] handle LaTex file
|
|
||||||
- [X] add pdf to latex tab for easy conversion of math pdf into readble math for LLM (added with nougat)
|
|
||||||
|
|
||||||
- [ ] Add references text box, to show references used by the models
|
- [ ] Add special support for code PDF (with specialized langchain code spliter)
|
||||||
|
- [ ] Add Multimodality
|
||||||
|
|
||||||
|
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue