Paper Metadata (v1)

This example extracts metadata (title, authors, abstract) from PDF papers, stores it in Postgres, and builds embeddings for semantic search.

We appreciate a star ⭐ at CocoIndex Github if this is helpful.

Prerequisites

A running Postgres with the pgvector extension. If you don't have one, start a local instance with the compose file in this repo:
sh
```
docker compose -f ../../dev/postgres.yaml up -d
```
Set OPENAI_API_KEY for metadata extraction
Set POSTGRES_URL for Postgres access

Install dependencies:

pip install -e .

Set environment variables:

export OPENAI_API_KEY="your_key"
export POSTGRES_URL="postgres://cocoindex:cocoindex@localhost/cocoindex"

This example uses the coco_examples_v1 schema by default to avoid clashing with the legacy example tables.

Build/update the index. Either of the following works:

cocoindex update main

python main.py

Query:

python main.py query "graph neural networks"

Note: this example does not create a vector index; queries will do a sequential scan.