apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-04-24 23:56:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Update demo example paper and polish README

Browse source
This commit is contained in:
Ray 2026-03-27 01:22:03 +08:00
parent 5d4491f3bf
commit 9798aaae19
3 changed files with 12 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

1
.gitignore vendored
View file

@ -7,6 +7,7 @@ chroma-collections.parquet
chroma-embeddings.parquet
.DS_Store
.env*
.venv/
notebook
SDK/*
log/*

11
README.md
View file

@ -101,6 +101,7 @@ The PageIndex service is available as a ChatGPT-style [chat platform](https://ch
---
# 🌲 PageIndex Tree Structure
PageIndex can transform lengthy PDF documents into a semantic **tree structure**, similar to a _"table of contents"_ but optimized for use with Large Language Models (LLMs). It's ideal for: financial reports, regulatory filings, academic textbooks, legal or technical manuals, and any document that exceeds LLM context limits.
Below is an example PageIndex tree structure. Also see more example [documents](https://github.com/VectifyAI/PageIndex/tree/main/tests/pdfs) and generated [tree structures](https://github.com/VectifyAI/PageIndex/tree/main/tests/results).
@ -133,7 +134,7 @@ Below is an example PageIndex tree structure. Also see more example [documents](
...
```
You can generate the PageIndex tree structure with this open-source repo, or use our [API](https://docs.pageindex.ai/quickstart)
You can generate the PageIndex tree structure with this open-source repo, or use our [API](https://docs.pageindex.ai/quickstart).
---
@ -149,7 +150,7 @@ pip3 install --upgrade -r requirements.txt
### 2. Set your LLM API key
Create a `.env` file in the root directory with your LLM API key::
Create a `.env` file in the root directory with your LLM API key, with multi-LLM support via [LiteLLM](https://docs.litellm.ai/docs/providers):
```bash
OPENAI_API_KEY=your_openai_key_here
@ -169,7 +170,7 @@ python3 run_pageindex.py --pdf_path /path/to/your/document.pdf
You can customize the processing with additional optional arguments:
```
--model OpenAI model to use (default: gpt-4o-2024-11-20)
--model LLM model to use (default: gpt-4o-2024-11-20)
--toc-check-pages Pages to check for table of contents (default: 20)
--max-pages-per-node Max pages per node (default: 10)
--max-tokens-per-node Max tokens per node (default: 20000)
@ -182,7 +183,7 @@ You can customize the processing with additional optional arguments:
<details>
<summary><strong>Markdown support</strong></summary>
<br>
We also provide markdown support for PageIndex. You can use the `-md_path` flag to generate a tree structure for a markdown file.
We also provide markdown support for PageIndex. You can use the `--md_path` flag to generate a tree structure for a markdown file.
```bash
python3 run_pageindex.py --md_path /path/to/your/document.md
@ -193,7 +194,7 @@ python3 run_pageindex.py --md_path /path/to/your/document.md
### A Complete Agentic RAG Example
For a complete agent-based QA example using the [OpenAI Agents SDK](https://github.com/openai/openai-agents-python), see [`examples/openai_agents_demo.py`](examples/openai_agents_demo.py).
For a complete example on **agentic RAG with PageIndex** (using [OpenAI Agents SDK](https://github.com/openai/openai-agents-python)), see [`examples/openai_agents_demo.py`](examples/openai_agents_demo.py).
```bash
# Install optional dependency

6
examples/openai_agents_demo.py
View file

@ -32,8 +32,8 @@ from openai.types.responses import ResponseTextDeltaEvent, ResponseReasoningSumm
from pageindex import PageIndexClient
import pageindex.utils as utils
PDF_URL = "https://arxiv.org/pdf/2501.12948.pdf"
PDF_PATH = "tests/pdfs/deepseek-r1.pdf"
PDF_URL = "https://arxiv.org/pdf/2603.15031"
PDF_PATH = "tests/pdfs/attention-residuals.pdf"
WORKSPACE = "./pageindex_workspace"
AGENT_SYSTEM_PROMPT = """
@ -168,6 +168,6 @@ print(client.get_document(doc_id))
print("\n" + "=" * 60)
print("Step 3: Agent Query (auto tool-use)")
print("=" * 60)
question = "What reward design does DeepSeek-R1-Zero use, and why was it chosen over supervised fine-tuning?"
question = "Explain Attention Residuals in simple language."
print(f"\nQuestion: '{question}'\n")
query_agent(client, doc_id, question, verbose=True)