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

fix image

Browse source
This commit is contained in:
zmtomorrow 2025-08-22 10:14:21 +01:00
parent af64e253f5
commit 116b54279c
1 changed files with 19 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

37
cookbook/pageindex_RAG_simple.ipynb
View file

@ -40,12 +40,16 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"PageIndex generates a searchable tree structure of documents, enabling reasoning-based retrieval through tree search. \n",
"## Introduction\n",
"PageIndex is a new **vectorless RAG** framework. It conduct retrieval in two steps: \n",
"1. Generate a tree structure to index documents \n",
"2. Perform reasoning-based retrieval through tree search \n",
"\n",
"<div align=\"center\">\n",
" <img src=\"https://pageindex.ai/static/images/vectorless_rag_workflow.png\" width=\"100%\">\n",
" <img src=\"https://pageindex.ai/static/images/vectorless_rag_workflow.png\" width=\"70%\">\n",
"</div>\n",
"\n",
"Compared to classic vector-based RAG, PageIndex features:\n",
"- **No Vectors Needed**: Uses document structure and LLM reasoning for retrieval.\n",
"- **No Chunking Needed**: Documents are organized into natural sections rather than artificial chunks.\n",
"- **Human-like Retrieval**: Simulates how human experts navigate and extract knowledge from complex documents. \n",
@ -61,21 +65,18 @@
"This notebook demonstrates a simple example of **vectorless RAG** with PageIndex through the following steps:\n",
"- [x] Build a PageIndex tree structure of a document\n",
"- [x] Perform reasoning-based retrieval with tree search\n",
"- [x] Generate answers based on the retrieved context"
"- [x] Generate answers based on the retrieved context\n",
"\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "7ziuTbbWcG1L"
},
"source": [
"## Preparation\n",
"## Step 0: Preparation\n",
"\n"
]
},
@ -85,7 +86,7 @@
"id": "edTfrizMFK4c"
},
"source": [
"### Install dependencies"
"#### 0.1 Install dependencies"
]
},
{
@ -106,7 +107,7 @@
"id": "WVEWzPKGcG1M"
},
"source": [
"### Setup environment"
"#### 0.2 Setup environment"
]
},
{
@ -134,7 +135,7 @@
"id": "AR7PLeVbcG1N"
},
"source": [
"### Define utility functions"
"#### 0.3 Define utility functions"
]
},
{
@ -198,7 +199,7 @@
"id": "Mzd1VWjwMUJL"
},
"source": [
"### Submit a document with PageIndex SDK"
"#### 1.1 Submit a document with PageIndex SDK"
]
},
{
@ -244,7 +245,7 @@
"id": "4-Hrh0azcG1N"
},
"source": [
"### Get the generated PageIndex tree structure"
"#### 1.2 Get the generated PageIndex tree structure"
]
},
{
@ -356,7 +357,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"### Use LLM for tree search and identify nodes that might contain relevant context"
"#### 2.1 Use LLM for tree search and identify nodes that might contain relevant context"
]
},
{
@ -396,7 +397,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"### Print retrieved nodes and reasoning process"
"#### 2.2 Print retrieved nodes and reasoning process"
]
},
{
@ -455,7 +456,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"### Extract relevant context from retrieved nodes"
"#### 3.1 Extract relevant context from retrieved nodes"
]
},
{
@ -507,7 +508,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"### Generate answer based on retrieved context"
"#### 3.2 Generate answer based on retrieved context"
]
},
{