NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: added markdown headings to enable TOC in github pages (#808)

Browse Source 
* docs: added markdown headings to enable TOC in github pages

Signed-off-by: Farzad Sunavala <40604067+farzad528@users.noreply.github.com>

* minor renames

Signed-off-by: Farzad Sunavala <40604067+farzad528@users.noreply.github.com>

* part 3 heading

Signed-off-by: Farzad Sunavala <40604067+farzad528@users.noreply.github.com>

---------

Signed-off-by: Farzad Sunavala <40604067+farzad528@users.noreply.github.com>
This commit is contained in:
Farzad Sunavala 2025-01-27 02:40:35 -06:00 committed by GitHub
parent c2ae1cc4ca
commit b885b2fa3c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docs/examples/rag_azuresearch.ipynb
View File

@ -33,6 +33,7 @@
"metadata": {},
"source": [
"\n",
"## A recipe 🧑‍🍳 🐥 💚\n",
"\n",
"This notebook demonstrates how to build a Retrieval-Augmented Generation (RAG) system using:\n",
"- [Docling](https://ds4sd.github.io/docling/) for document parsing and chunking\n",
@ -61,7 +62,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"# Part 0: Prerequisites\n",
"### Part 0: Prerequisites\n",
" - **Azure AI Search** resource\n",
" - **Azure OpenAI** resource with a deployed embedding and chat completion model (e.g. `text-embedding-3-small` and `gpt-4o`) \n",
" - **Docling 2.12+** (installs `docling_core` automatically) Docling installed (Python 3.8+ environment)\n",
@ -114,7 +115,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## Part 1: Parse the PDF with Docling\n",
"### Part 1: Parse the PDF with Docling\n",
"\n",
"We’ll parse the **Microsoft GraphRAG Research Paper** (~15 pages). Parsing should be relatively quick, even on CPU, but it will be faster on a GPU or MPS device if available.\n",
"\n",
@ -235,7 +236,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"# Part 2: Hierarchical Chunking\n",
"### Part 2: Hierarchical Chunking\n",
"We convert the `Document` into smaller chunks for embedding and indexing. The built-in `HierarchicalChunker` preserves structure. "
]
},
@ -276,7 +277,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"# Part 3: Create Azure Search Index and Push Chunk Embeddings\n",
"### Part 3: Create Azure Search Index and Push Chunk Embeddings\n",
"We’ll define a vector index in Azure AI Search, then embed each chunk using Azure OpenAI and upload in batches."
]
},
@ -382,7 +383,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"### Embed and Upsert to Azure AI Search\n"
"#### Generate Embeddings and Upload to Azure AI Search\n"
]
},
{
@ -497,8 +498,8 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"# Part 4: RAG Query with Azure OpenAI\n",
"Combine retrieval from Azure Search with Chat Completions (aka. grounding your LLM)"
"### Part 4: Perform RAG I\n",
"Combine retrieval from Azure AI Search with Azure OpenAI Chat Completions (aka. grounding your LLM)"
]
},
{