Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -234,7 +234,7 @@ recommender = SemanticSearch()
|
|
234 |
|
235 |
title = 'Cognitive pdfGPT'
|
236 |
description = """ What is Cognitive pdfGPT?
|
237 |
-
The
|
238 |
|
239 |
|
240 |
|
|
|
234 |
|
235 |
title = 'Cognitive pdfGPT'
|
236 |
description = """ What is Cognitive pdfGPT?
|
237 |
+
The issue is OpenAI has a 4K token constraint, preventing it from processing an entire PDF file as input. Additionally, ChatGPT cannot (as of yet) directly talk to external data. The solution is Cognitive pdfGPT, which allows you to chat with your PDF file using GPT functionalities. The application converts the document into smaller files and generates embeddings using a powerful Deep Averaging Network Encoder. A semantic search is performed on your data, and the top relevant results are used to generate a response. 🛑DO NOT USE CONFIDENTIAL INFORMATION """
|
238 |
|
239 |
|
240 |
|