llm_aided_ocr

llm_aided_ocr copied to clipboard

Alternative offline LLMs

2

Hi, Your code used llma2 chat offline LLM. But, I wanted to use alternative offline LLMs such as huggingface's distilbert or roberta or albert. Do you have any suggestion for...

adnanPBI

Support APIs

2

Is there any plan to restructure the code to be uniform to use it with Llama2/API like (gpt-3.5-turbo, gpt-4) to use this PDF-to-text in any hardware. https://github.com/Dicklesworthstone/llama2_aided_tesseract/blob/5719a9aede6b0666f6f08d239cac7b1550298b79/tesseract_with_llama2_corrections.py#L180 https://github.com/Dicklesworthstone/llama2_aided_tesseract/blob/5719a9aede6b0666f6f08d239cac7b1550298b79/tesseract_with_llama2_corrections.py#L122 https://github.com/Dicklesworthstone/llama2_aided_tesseract/blob/5719a9aede6b0666f6f08d239cac7b1550298b79/tesseract_with_llama2_corrections.py#L173

ayoubelmhamdi

include original images/charts/tables to output doc

1

for these `doc format convertion`, `text summarization` tasks, I think one of key feature is to include all or some of the images/charts/tables from original doc, as those elements often...

shaojun

Your provided [tesseract_with_llama2_corrections.py] code snippet is equipped with the llma2 chat ggml q3 k_s.bin LLM model but the huggingface.co is referring to use GGUF instead saying the GGML is deprecated....

adnanPBI

ERROR: Failed building wheel for llama-cpp-python

1

ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (llama-cpp-python) I have updated the gcc version but still the error. Working for ubuntu verison 24.04 LTS but...

SouravaBehera

Taking a lot of time for the sample pdf

3

I am using a 16 core cpu for the same document using a local model same as in the github repo. How to get the output faster?

SouravaBehera

Any alternate local model?

2

Token indices sequence length is longer than the specified maximum sequence length for this model (2816 > 2048). Running this sequence through the model will result in indexing errors 2024-08-13...

SouravaBehera

Negative max_tokens value

1

I am getting negative max tokens in AI call.. Some small bug probably... ``` 2024-08-12 09:54:03,183 - ERROR - An error occurred while processing a chunk: Error code: 400 -...

chew-z

It would be super nice to integrate this with https://github.com/ocrmypdf/OCRmyPDF

tcurdt

Failed to Load Model From file

1

Even after properly following the instructions, it throws error: ValueError: Failed to load model from file: .Llama-2-13B-chat-GGML/llama-2-13b-chat.ggmlv3.q4_K_S.bin I have checked with all other model files, same error persists

BichitraAI