Generate PDF and DOCX file embeddings using OpenAI in Python

Extract text from PDF or DOCX files and create embeddings with OpenAI’s API. Set file paths, read and split text into chunks, generate embeddings for each chunk, and store the results.

Required packages

You need below packages to use the code generated by recipe. All packages are automatically installed in MLJAR Studio.

openai>=1.35.14

pypdf>=4.1.0

python-docx>=1.1.2

Interactive recipe

You can use below interactive recipe to generate code. This recipe is available in MLJAR Studio.

In the below recipe, we assume that you have following variables available in your notebook:

client (type OpenAI)

Python code

# Python code will be here

Code explanation

Set the file path.
Read the file.
Split text from the file into chunks.
Generate embeddings for each chunk.

Example Python notebooks

Please find inspiration in example notebooks

Generate embeddings for whole files using OpenAI in Python
How to search the cosine similarity using OpenAI in Python
Build RAG App using OpenAI in Python

OpenAI cookbook

Code recipes from OpenAI cookbook.

Client connection
Chat completions
Cosine similarity search
Embeddings
Files embeddings
AI images generator
Speech transcriptions
Speech translations
Text to speech
Vision with local images
Vision with URL images

« Previous: Embeddings
Next »: AI image generator