-
Notifications
You must be signed in to change notification settings - Fork 120
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
3 changed files
with
65 additions
and
4 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
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 |
---|---|---|
@@ -0,0 +1,63 @@ | ||
{ | ||
"cells": [ | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"## **PDF Extraction**\n", | ||
"We've curated a collection of inspiring examples to showcase the versatility of PDF extraction. Check out these notebooks:\n", | ||
"\n", | ||
"#### RAG based Question Answering\n", | ||
"- [Efficient and supercharged RAG for mixed context texts with Indexify's framework, Gemini's 1M context & Arctic's embeddings](./efficient_rag.ipynb)\n", | ||
"- [Question Answering from PDF using Indexify and OpenAI](./pdfqa.ipynb)\n", | ||
"- [Scientific Journals](./Scientific_Journals.ipynb)\n", | ||
"\n", | ||
"#### Schema based Extractions\n", | ||
"- [Schema based HOA Documents](./HOA_Invoice_Data_Extraction.ipynb)\n", | ||
"- [SEC 10-K docs](./SEC_10_K_docs.ipynb)\n", | ||
"\n", | ||
"#### LLM based Extractions\n", | ||
"- [Entity Recognition from PDF using Indexify and Gemini](https://colab.research.google.com/drive/1gHru2qjEhl4cmAOTQMj7unHnQACCh7We?usp=sharing)\n", | ||
"- [Invoices](./Invoices.ipynb): Extract and analyze invoice data like a pro!\n", | ||
"\n", | ||
"#### Terms and Condition Documents\n", | ||
"- [Multi-state Terms Documents](./Sixt.ipynb)\n", | ||
"- [Terms and Condition Documents of Car Rental](./Terms_and_Condition_Documents_of_Car_Rental.ipynb): Navigate the complex world of car rental agreements with ease.\n", | ||
"- [Terms and Conditions Documents of Health Care Benefits](./Terms_and_Conditions_Documents_of_Health_Care_Benefits.ipynb): Demystify health care benefits and make informed decisions." | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"## **Audio Extraction**\n", | ||
"Check out this inspiring example to showcase the power of audio based extraction:\n", | ||
"\n", | ||
"- [ASR Diarization Colab Notebook](https://colab.research.google.com/drive/1aW6DdAkxTQWZcCe1fS0QCVZ6GeQFji2S?usp=sharing): Experience the state-of-the-art ASR + diarization + speculative decoding capabilities.\n", | ||
"- [RAG using Audio as a Context](./audio_rag.ipynb)\n", | ||
"- [Transcribing Audio with Indexify](./audio_transcription.ipynb)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"## **Image & Video Extraction**\n", | ||
"Check out this inspiring example to showcase the power of image & video based extraction:\n", | ||
"\n", | ||
"- [GIF search with MiniLM-L6 and CLIP embeddings](./GifSearch.ipynb)\n", | ||
"- [Accurate Image RAG using Yolo and CodeGemma](./Image_RAG_Structured_Extraction.ipynb)\n", | ||
"- [Indexing Images Based on Visual Description](./Moondream_Visual_Description_Index.ipynb)\n", | ||
"- [RAG using Video as Context](./Video_RAG.ipynb)\n", | ||
"- [Indexing Video Based on Visual Understanding](./Visual_Understanding_Clip_Yolo.ipynb)" | ||
] | ||
} | ||
], | ||
"metadata": { | ||
"language_info": { | ||
"name": "python" | ||
} | ||
}, | ||
"nbformat": 4, | ||
"nbformat_minor": 2 | ||
} |
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