{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "Ag9kcX2B_atc"
},
"source": [
"![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\")
"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# RAG with Azure AI Search"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"| Step | Tech | Execution |\n",
"| ------------------ | ------------------ | --------- |\n",
"| Embedding | Azure OpenAI | ๐ Remote |\n",
"| Vector Store | Azure AI Search | ๐ Remote |\n",
"| Gen AI | Azure OpenAI | ๐ Remote |"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"## A recipe ๐งโ๐ณ ๐ฅ ๐\n",
"\n",
"This notebook demonstrates how to build a Retrieval-Augmented Generation (RAG) system using:\n",
"- [Docling](https://docling-project.github.io/docling/) for document parsing and chunking\n",
"- [Azure AI Search](https://azure.microsoft.com/products/ai-services/ai-search/?msockid=0109678bea39665431e37323ebff6723) for vector indexing and retrieval\n",
"- [Azure OpenAI](https://azure.microsoft.com/products/ai-services/openai-service?msockid=0109678bea39665431e37323ebff6723) for embeddings and chat completion\n",
"\n",
"This sample demonstrates how to:\n",
"1. Parse a PDF with Docling.\n",
"2. Chunk the parsed text.\n",
"3. Use Azure OpenAI for embeddings.\n",
"4. Index and search in Azure AI Search.\n",
"5. Run a retrieval-augmented generation (RAG) query with Azure OpenAI GPT-4o.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# If running in a fresh environment (like Google Colab), uncomment and run this single command:\n",
"%pip install \"docling~=2.12\" azure-search-documents==11.5.2 azure-identity openai rich torch python-dotenv"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 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",
"\n",
"- A **GPU-enabled environment** is preferred for faster parsing. Docling 2.12 automatically detects GPU if present.\n",
" - If you only have CPU, parsing large PDFs can be slower. "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"from dotenv import load_dotenv\n",
"\n",
"load_dotenv()\n",
"\n",
"\n",
"def _get_env(key, default=None):\n",
" try:\n",
" from google.colab import userdata\n",
"\n",
" try:\n",
" return userdata.get(key)\n",
" except userdata.SecretNotFoundError:\n",
" pass\n",
" except ImportError:\n",
" pass\n",
" return os.getenv(key, default)\n",
"\n",
"\n",
"AZURE_SEARCH_ENDPOINT = _get_env(\"AZURE_SEARCH_ENDPOINT\")\n",
"AZURE_SEARCH_KEY = _get_env(\"AZURE_SEARCH_KEY\") # Ensure this is your Admin Key\n",
"AZURE_SEARCH_INDEX_NAME = _get_env(\"AZURE_SEARCH_INDEX_NAME\", \"docling-rag-sample\")\n",
"AZURE_OPENAI_ENDPOINT = _get_env(\"AZURE_OPENAI_ENDPOINT\")\n",
"AZURE_OPENAI_API_KEY = _get_env(\"AZURE_OPENAI_API_KEY\")\n",
"AZURE_OPENAI_API_VERSION = _get_env(\"AZURE_OPENAI_API_VERSION\", \"2024-10-21\")\n",
"AZURE_OPENAI_CHAT_MODEL = _get_env(\n",
" \"AZURE_OPENAI_CHAT_MODEL\"\n",
") # Using a deployed model named \"gpt-4o\"\n",
"AZURE_OPENAI_EMBEDDINGS = _get_env(\n",
" \"AZURE_OPENAI_EMBEDDINGS\", \"text-embedding-3-small\"\n",
") # Using a deployed model named \"text-embeddings-3-small\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Part 1: Parse the PDF with Docling\n",
"\n",
"Weโll 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",
"*(If you prefer a different document, simply provide a different URL or local file path.)*"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"Parsing a ~15-page PDF. The process should be relatively quick, even on CPU...\n",
"\n"
],
"text/plain": [
"\u001b[1;33mParsing a ~\u001b[0m\u001b[1;33m15\u001b[0m\u001b[1;33m-page PDF. The process should be relatively quick, even on CPU\u001b[0m\u001b[1;33m...\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"โญโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ Docling Markdown Preview โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฎ\n",
"โ ## From Local to Global: A Graph RAG Approach to Query-Focused Summarization โ\n",
"โ โ\n",
"โ Darren Edge 1โ โ\n",
"โ โ\n",
"โ Ha Trinh 1โ โ\n",
"โ โ\n",
"โ Newman Cheng 2 โ\n",
"โ โ\n",
"โ Joshua Bradley 2 โ\n",
"โ โ\n",
"โ Alex Chao 3 โ\n",
"โ โ\n",
"โ Apurva Mody 3 โ\n",
"โ โ\n",
"โ Steven Truitt 2 โ\n",
"โ โ\n",
"โ ## Jonathan Larson 1 โ\n",
"โ โ\n",
"โ 1 Microsoft Research 2 Microsoft Strategic Missions and Technologies 3 Microsoft Office of the CTO โ\n",
"โ โ\n",
"โ { daedge,trinhha,newmancheng,joshbradley,achao,moapurva,steventruitt,jolarso } @microsoft.com โ\n",
"โ โ\n",
"โ โ These authors contributed equally to this work โ\n",
"โ โ\n",
"โ ## Abstract โ\n",
"โ โ\n",
"โ The use of retrieval-augmented gen... โ\n",
"โฐโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฏ\n",
"\n"
],
"text/plain": [
"โญโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ Docling Markdown Preview โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฎ\n",
"โ ## From Local to Global: A Graph RAG Approach to Query-Focused Summarization โ\n",
"โ โ\n",
"โ Darren Edge 1โ โ\n",
"โ โ\n",
"โ Ha Trinh 1โ โ\n",
"โ โ\n",
"โ Newman Cheng 2 โ\n",
"โ โ\n",
"โ Joshua Bradley 2 โ\n",
"โ โ\n",
"โ Alex Chao 3 โ\n",
"โ โ\n",
"โ Apurva Mody 3 โ\n",
"โ โ\n",
"โ Steven Truitt 2 โ\n",
"โ โ\n",
"โ ## Jonathan Larson 1 โ\n",
"โ โ\n",
"โ 1 Microsoft Research 2 Microsoft Strategic Missions and Technologies 3 Microsoft Office of the CTO โ\n",
"โ โ\n",
"โ { daedge,trinhha,newmancheng,joshbradley,achao,moapurva,steventruitt,jolarso } @microsoft.com โ\n",
"โ โ\n",
"โ โ These authors contributed equally to this work โ\n",
"โ โ\n",
"โ ## Abstract โ\n",
"โ โ\n",
"โ The use of retrieval-augmented gen... โ\n",
"โฐโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฏ\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from rich.console import Console\n",
"from rich.panel import Panel\n",
"\n",
"from docling.document_converter import DocumentConverter\n",
"\n",
"console = Console()\n",
"\n",
"# This URL points to the Microsoft GraphRAG Research Paper (arXiv: 2404.16130), ~15 pages\n",
"source_url = \"https://arxiv.org/pdf/2404.16130\"\n",
"\n",
"console.print(\n",
" \"[bold yellow]Parsing a ~15-page PDF. The process should be relatively quick, even on CPU...[/bold yellow]\"\n",
")\n",
"converter = DocumentConverter()\n",
"result = converter.convert(source_url)\n",
"\n",
"# Optional: preview the parsed Markdown\n",
"md_preview = result.document.export_to_markdown()\n",
"console.print(Panel(md_preview[:500] + \"...\", title=\"Docling Markdown Preview\"))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Part 2: Hierarchical Chunking\n",
"We convert the `Document` into smaller chunks for embedding and indexing. The built-in `HierarchicalChunker` preserves structure. "
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"Total chunks from PDF: 106\n",
"\n"
],
"text/plain": [
"Total chunks from PDF: \u001b[1;36m106\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from docling.chunking import HierarchicalChunker\n",
"\n",
"chunker = HierarchicalChunker()\n",
"doc_chunks = list(chunker.chunk(result.document))\n",
"\n",
"all_chunks = []\n",
"for idx, c in enumerate(doc_chunks):\n",
" chunk_text = c.text\n",
" all_chunks.append((f\"chunk_{idx}\", chunk_text))\n",
"\n",
"console.print(f\"Total chunks from PDF: {len(all_chunks)}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Part 3: Create Azure AI Search Index and Push Chunk Embeddings\n",
"Weโll define a vector index in Azure AI Search, then embed each chunk using Azure OpenAI and upload in batches."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"Index 'docling-rag-sample-2' created.\n",
"\n"
],
"text/plain": [
"Index \u001b[32m'docling-rag-sample-2'\u001b[0m created.\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from azure.core.credentials import AzureKeyCredential\n",
"from azure.search.documents.indexes import SearchIndexClient\n",
"from azure.search.documents.indexes.models import (\n",
" AzureOpenAIVectorizer,\n",
" AzureOpenAIVectorizerParameters,\n",
" HnswAlgorithmConfiguration,\n",
" SearchableField,\n",
" SearchField,\n",
" SearchFieldDataType,\n",
" SearchIndex,\n",
" SimpleField,\n",
" VectorSearch,\n",
" VectorSearchProfile,\n",
")\n",
"from rich.console import Console\n",
"\n",
"console = Console()\n",
"\n",
"VECTOR_DIM = 1536 # Adjust based on your chosen embeddings model\n",
"\n",
"index_client = SearchIndexClient(\n",
" AZURE_SEARCH_ENDPOINT, AzureKeyCredential(AZURE_SEARCH_KEY)\n",
")\n",
"\n",
"\n",
"def create_search_index(index_name: str):\n",
" # Define fields\n",
" fields = [\n",
" SimpleField(name=\"chunk_id\", type=SearchFieldDataType.String, key=True),\n",
" SearchableField(name=\"content\", type=SearchFieldDataType.String),\n",
" SearchField(\n",
" name=\"content_vector\",\n",
" type=SearchFieldDataType.Collection(SearchFieldDataType.Single),\n",
" searchable=True,\n",
" filterable=False,\n",
" sortable=False,\n",
" facetable=False,\n",
" vector_search_dimensions=VECTOR_DIM,\n",
" vector_search_profile_name=\"default\",\n",
" ),\n",
" ]\n",
" # Vector search config with an AzureOpenAIVectorizer\n",
" vector_search = VectorSearch(\n",
" algorithms=[HnswAlgorithmConfiguration(name=\"default\")],\n",
" profiles=[\n",
" VectorSearchProfile(\n",
" name=\"default\",\n",
" algorithm_configuration_name=\"default\",\n",
" vectorizer_name=\"default\",\n",
" )\n",
" ],\n",
" vectorizers=[\n",
" AzureOpenAIVectorizer(\n",
" vectorizer_name=\"default\",\n",
" parameters=AzureOpenAIVectorizerParameters(\n",
" resource_url=AZURE_OPENAI_ENDPOINT,\n",
" deployment_name=AZURE_OPENAI_EMBEDDINGS,\n",
" model_name=\"text-embedding-3-small\",\n",
" api_key=AZURE_OPENAI_API_KEY,\n",
" ),\n",
" )\n",
" ],\n",
" )\n",
"\n",
" # Create or update the index\n",
" new_index = SearchIndex(name=index_name, fields=fields, vector_search=vector_search)\n",
" try:\n",
" index_client.delete_index(index_name)\n",
" except Exception:\n",
" pass\n",
"\n",
" index_client.create_or_update_index(new_index)\n",
" console.print(f\"Index '{index_name}' created.\")\n",
"\n",
"\n",
"create_search_index(AZURE_SEARCH_INDEX_NAME)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Generate Embeddings and Upload to Azure AI Search\n"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"Uploaded batch 0 -> 50; all_succeeded: True, first_doc_status_code: 201\n",
"\n"
],
"text/plain": [
"Uploaded batch \u001b[1;36m0\u001b[0m -> \u001b[1;36m50\u001b[0m; all_succeeded: \u001b[3;92mTrue\u001b[0m, first_doc_status_code: \u001b[1;36m201\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Uploaded batch 50 -> 100; all_succeeded: True, first_doc_status_code: 201\n",
"\n"
],
"text/plain": [
"Uploaded batch \u001b[1;36m50\u001b[0m -> \u001b[1;36m100\u001b[0m; all_succeeded: \u001b[3;92mTrue\u001b[0m, first_doc_status_code: \u001b[1;36m201\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Uploaded batch 100 -> 106; all_succeeded: True, first_doc_status_code: 201\n",
"\n"
],
"text/plain": [
"Uploaded batch \u001b[1;36m100\u001b[0m -> \u001b[1;36m106\u001b[0m; all_succeeded: \u001b[3;92mTrue\u001b[0m, first_doc_status_code: \u001b[1;36m201\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"All chunks uploaded to Azure Search.\n",
"\n"
],
"text/plain": [
"All chunks uploaded to Azure Search.\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from azure.search.documents import SearchClient\n",
"from openai import AzureOpenAI\n",
"\n",
"search_client = SearchClient(\n",
" AZURE_SEARCH_ENDPOINT, AZURE_SEARCH_INDEX_NAME, AzureKeyCredential(AZURE_SEARCH_KEY)\n",
")\n",
"openai_client = AzureOpenAI(\n",
" api_key=AZURE_OPENAI_API_KEY,\n",
" api_version=AZURE_OPENAI_API_VERSION,\n",
" azure_endpoint=AZURE_OPENAI_ENDPOINT,\n",
")\n",
"\n",
"\n",
"def embed_text(text: str):\n",
" \"\"\"\n",
" Helper to generate embeddings with Azure OpenAI.\n",
" \"\"\"\n",
" response = openai_client.embeddings.create(\n",
" input=text, model=AZURE_OPENAI_EMBEDDINGS\n",
" )\n",
" return response.data[0].embedding\n",
"\n",
"\n",
"upload_docs = []\n",
"for chunk_id, chunk_text in all_chunks:\n",
" embedding_vector = embed_text(chunk_text)\n",
" upload_docs.append(\n",
" {\n",
" \"chunk_id\": chunk_id,\n",
" \"content\": chunk_text,\n",
" \"content_vector\": embedding_vector,\n",
" }\n",
" )\n",
"\n",
"\n",
"BATCH_SIZE = 50\n",
"for i in range(0, len(upload_docs), BATCH_SIZE):\n",
" subset = upload_docs[i : i + BATCH_SIZE]\n",
" resp = search_client.upload_documents(documents=subset)\n",
"\n",
" all_succeeded = all(r.succeeded for r in resp)\n",
" console.print(\n",
" f\"Uploaded batch {i} -> {i + len(subset)}; all_succeeded: {all_succeeded}, \"\n",
" f\"first_doc_status_code: {resp[0].status_code}\"\n",
" )\n",
"\n",
"console.print(\"All chunks uploaded to Azure Search.\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Part 4: Perform RAG over PDF\n",
"Combine retrieval from Azure AI Search with Azure OpenAI Chat Completions (aka. grounding your LLM)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"โญโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ RAG Prompt โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฎ\n",
"โ โ\n",
"โ You are an AI assistant helping answering questions about Microsoft GraphRAG. โ\n",
"โ Use ONLY the text below to answer the user's question. โ\n",
"โ If the answer isn't in the text, say you don't know. โ\n",
"โ โ\n",
"โ Context: โ\n",
"โ Community summaries vs. source texts. When comparing community summaries to source texts using Graph RAG, โ\n",
"โ community summaries generally provided a small but consistent improvement in answer comprehensiveness and โ\n",
"โ diversity, except for root-level summaries. Intermediate-level summaries in the Podcast dataset and low-level โ\n",
"โ community summaries in the News dataset achieved comprehensiveness win rates of 57% and 64%, respectively. โ\n",
"โ Diversity win rates were 57% for Podcast intermediate-level summaries and 60% for News low-level community โ\n",
"โ summaries. Table 3 also illustrates the scalability advantages of Graph RAG compared to source text โ\n",
"โ summarization: for low-level community summaries ( C3 ), Graph RAG required 26-33% fewer context tokens, while โ\n",
"โ for root-level community summaries ( C0 ), it required over 97% fewer tokens. For a modest drop in performance โ\n",
"โ compared with other global methods, root-level Graph RAG offers a highly efficient method for the iterative โ\n",
"โ question answering that characterizes sensemaking activity, while retaining advantages in comprehensiveness โ\n",
"โ (72% win rate) and diversity (62% win rate) over naยจฤฑve RAG. โ\n",
"โ --- โ\n",
"โ We have presented a global approach to Graph RAG, combining knowledge graph generation, retrieval-augmented โ\n",
"โ generation (RAG), and query-focused summarization (QFS) to support human sensemaking over entire text corpora. โ\n",
"โ Initial evaluations show substantial improvements over a naยจฤฑve RAG baseline for both the comprehensiveness and โ\n",
"โ diversity of answers, as well as favorable comparisons to a global but graph-free approach using map-reduce โ\n",
"โ source text summarization. For situations requiring many global queries over the same dataset, summaries of โ\n",
"โ root-level communities in the entity-based graph index provide a data index that is both superior to naยจฤฑve RAG โ\n",
"โ and achieves competitive performance to other global methods at a fraction of the token cost. โ\n",
"โ --- โ\n",
"โ Trade-offs of building a graph index . We consistently observed Graph RAG achieve the best headto-head results โ\n",
"โ against other methods, but in many cases the graph-free approach to global summarization of source texts โ\n",
"โ performed competitively. The real-world decision about whether to invest in building a graph index depends on โ\n",
"โ multiple factors, including the compute budget, expected number of lifetime queries per dataset, and value โ\n",
"โ obtained from other aspects of the graph index (including the generic community summaries and the use of other โ\n",
"โ graph-related RAG approaches). โ\n",
"โ --- โ\n",
"โ Future work . The graph index, rich text annotations, and hierarchical community structure supporting the โ\n",
"โ current Graph RAG approach offer many possibilities for refinement and adaptation. This includes RAG approaches โ\n",
"โ that operate in a more local manner, via embedding-based matching of user queries and graph annotations, as โ\n",
"โ well as the possibility of hybrid RAG schemes that combine embedding-based matching against community reports โ\n",
"โ before employing our map-reduce summarization mechanisms. This 'roll-up' operation could also be extended โ\n",
"โ across more levels of the community hierarchy, as well as implemented as a more exploratory 'drill down' โ\n",
"โ mechanism that follows the information scent contained in higher-level community summaries. โ\n",
"โ --- โ\n",
"โ Advanced RAG systems include pre-retrieval, retrieval, post-retrieval strategies designed to overcome the โ\n",
"โ drawbacks of Naยจฤฑve RAG, while Modular RAG systems include patterns for iterative and dynamic cycles of โ\n",
"โ interleaved retrieval and generation (Gao et al., 2023). Our implementation of Graph RAG incorporates multiple โ\n",
"โ concepts related to other systems. For example, our community summaries are a kind of self-memory (Selfmem, โ\n",
"โ Cheng et al., 2024) for generation-augmented retrieval (GAR, Mao et al., 2020) that facilitates future โ\n",
"โ generation cycles, while our parallel generation of community answers from these summaries is a kind of โ\n",
"โ iterative (Iter-RetGen, Shao et al., 2023) or federated (FeB4RAG, Wang et al., 2024) retrieval-generation โ\n",
"โ strategy. Other systems have also combined these concepts for multi-document summarization (CAiRE-COVID, Su et โ\n",
"โ al., 2020) and multi-hop question answering (ITRG, Feng et al., 2023; IR-CoT, Trivedi et al., 2022; DSP, โ\n",
"โ Khattab et al., 2022). Our use of a hierarchical index and summarization also bears resemblance to further โ\n",
"โ approaches, such as generating a hierarchical index of text chunks by clustering the vectors of text embeddings โ\n",
"โ (RAPTOR, Sarthi et al., 2024) or generating a 'tree of clarifications' to answer multiple interpretations of โ\n",
"โ ambiguous questions (Kim et al., 2023). However, none of these iterative or hierarchical approaches use the โ\n",
"โ kind of self-generated graph index that enables Graph RAG. โ\n",
"โ --- โ\n",
"โ The use of retrieval-augmented generation (RAG) to retrieve relevant information from an external knowledge โ\n",
"โ source enables large language models (LLMs) to answer questions over private and/or previously unseen document โ\n",
"โ collections. However, RAG fails on global questions directed at an entire text corpus, such as 'What are the โ\n",
"โ main themes in the dataset?', since this is inherently a queryfocused summarization (QFS) task, rather than an โ\n",
"โ explicit retrieval task. Prior QFS methods, meanwhile, fail to scale to the quantities of text indexed by โ\n",
"โ typical RAGsystems. To combine the strengths of these contrasting methods, we propose a Graph RAG approach to โ\n",
"โ question answering over private text corpora that scales with both the generality of user questions and the โ\n",
"โ quantity of source text to be indexed. Our approach uses an LLM to build a graph-based text index in two โ\n",
"โ stages: first to derive an entity knowledge graph from the source documents, then to pregenerate community โ\n",
"โ summaries for all groups of closely-related entities. Given a question, each community summary is used to โ\n",
"โ generate a partial response, before all partial responses are again summarized in a final response to the user. โ\n",
"โ For a class of global sensemaking questions over datasets in the 1 million token range, we show that Graph RAG โ\n",
"โ leads to substantial improvements over a naยจฤฑve RAG baseline for both the comprehensiveness and diversity of โ\n",
"โ generated answers. An open-source, Python-based implementation of both global and local Graph RAG approaches is โ\n",
"โ forthcoming at https://aka . ms/graphrag . โ\n",
"โ --- โ\n",
"โ Given the multi-stage nature of our Graph RAG mechanism, the multiple conditions we wanted to compare, and the โ\n",
"โ lack of gold standard answers to our activity-based sensemaking questions, we decided to adopt a head-to-head โ\n",
"โ comparison approach using an LLM evaluator. We selected three target metrics capturing qualities that are โ\n",
"โ desirable for sensemaking activities, as well as a control metric (directness) used as a indicator of validity. โ\n",
"โ Since directness is effectively in opposition to comprehensiveness and diversity, we would not expect any โ\n",
"โ method to win across all four metrics. โ\n",
"โ --- โ\n",
"โ Figure 1: Graph RAG pipeline using an LLM-derived graph index of source document text. This index spans nodes โ\n",
"โ (e.g., entities), edges (e.g., relationships), and covariates (e.g., claims) that have been detected, โ\n",
"โ extracted, and summarized by LLM prompts tailored to the domain of the dataset. Community detection (e.g., โ\n",
"โ Leiden, Traag et al., 2019) is used to partition the graph index into groups of elements (nodes, edges, โ\n",
"โ covariates) that the LLM can summarize in parallel at both indexing time and query time. The 'global answer' to โ\n",
"โ a given query is produced using a final round of query-focused summarization over all community summaries โ\n",
"โ reporting relevance to that query. โ\n",
"โ --- โ\n",
"โ Retrieval-augmented generation (RAG, Lewis et al., 2020) is an established approach to answering user questions โ\n",
"โ over entire datasets, but it is designed for situations where these answers are contained locally within โ\n",
"โ regions of text whose retrieval provides sufficient grounding for the generation task. Instead, a more โ\n",
"โ appropriate task framing is query-focused summarization (QFS, Dang, 2006), and in particular, query-focused โ\n",
"โ abstractive summarization that generates natural language summaries and not just concatenated excerpts (Baumel โ\n",
"โ et al., 2018; Laskar et al., 2020; Yao et al., 2017) . In recent years, however, such distinctions between โ\n",
"โ summarization tasks that are abstractive versus extractive, generic versus query-focused, and single-document โ\n",
"โ versus multi-document, have become less relevant. While early applications of the transformer architecture โ\n",
"โ showed substantial improvements on the state-of-the-art for all such summarization tasks (Goodwin et al., 2020; โ\n",
"โ Laskar et al., 2022; Liu and Lapata, 2019), these tasks are now trivialized by modern LLMs, including the GPT โ\n",
"โ (Achiam et al., 2023; Brown et al., 2020), Llama (Touvron et al., 2023), and Gemini (Anil et al., 2023) series, โ\n",
"โ all of which can use in-context learning to summarize any content provided in their context window. โ\n",
"โ --- โ\n",
"โ community descriptions provide complete coverage of the underlying graph index and the input documents it โ\n",
"โ represents. Query-focused summarization of an entire corpus is then made possible using a map-reduce approach: โ\n",
"โ first using each community summary to answer the query independently and in parallel, then summarizing all โ\n",
"โ relevant partial answers into a final global answer. โ\n",
"โ โ\n",
"โ Question: What are the main advantages of using the Graph RAG approach for query-focused summarization compared โ\n",
"โ to traditional RAG methods? โ\n",
"โ Answer: โ\n",
"โ โ\n",
"โฐโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฏ\n",
"\n"
],
"text/plain": [
"\u001b[1;31mโญโ\u001b[0m\u001b[1;31mโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ\u001b[0m RAG Prompt \u001b[1;31mโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ\u001b[0m\u001b[1;31mโโฎ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mYou are an AI assistant helping answering questions about Microsoft GraphRAG.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mUse ONLY the text below to answer the user's question.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mIf the answer isn't in the text, say you don't know.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mContext:\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mCommunity summaries vs. source texts. When comparing community summaries to source texts using Graph RAG, \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mcommunity summaries generally provided a small but consistent improvement in answer comprehensiveness and \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mdiversity, except for root-level summaries. Intermediate-level summaries in the Podcast dataset and low-level \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mcommunity summaries in the News dataset achieved comprehensiveness win rates of 57% and 64%, respectively. \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mDiversity win rates were 57% for Podcast intermediate-level summaries and 60% for News low-level community \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31msummaries. Table 3 also illustrates the scalability advantages of Graph RAG compared to source text \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31msummarization: for low-level community summaries ( C3 ), Graph RAG required 26-33% fewer context tokens, while \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mfor root-level community summaries ( C0 ), it required over 97% fewer tokens. For a modest drop in performance \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mcompared with other global methods, root-level Graph RAG offers a highly efficient method for the iterative \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mquestion answering that characterizes sensemaking activity, while retaining advantages in comprehensiveness \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m(72% win rate) and diversity (62% win rate) over naยจฤฑve RAG.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m---\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mWe have presented a global approach to Graph RAG, combining knowledge graph generation, retrieval-augmented \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mgeneration (RAG), and query-focused summarization (QFS) to support human sensemaking over entire text corpora. \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mInitial evaluations show substantial improvements over a naยจฤฑve RAG baseline for both the comprehensiveness and\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mdiversity of answers, as well as favorable comparisons to a global but graph-free approach using map-reduce \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31msource text summarization. For situations requiring many global queries over the same dataset, summaries of \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mroot-level communities in the entity-based graph index provide a data index that is both superior to naยจฤฑve RAG\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mand achieves competitive performance to other global methods at a fraction of the token cost.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m---\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mTrade-offs of building a graph index . We consistently observed Graph RAG achieve the best headto-head results \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31magainst other methods, but in many cases the graph-free approach to global summarization of source texts \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mperformed competitively. The real-world decision about whether to invest in building a graph index depends on \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mmultiple factors, including the compute budget, expected number of lifetime queries per dataset, and value \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mobtained from other aspects of the graph index (including the generic community summaries and the use of other \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mgraph-related RAG approaches).\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m---\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mFuture work . The graph index, rich text annotations, and hierarchical community structure supporting the \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mcurrent Graph RAG approach offer many possibilities for refinement and adaptation. This includes RAG approaches\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mthat operate in a more local manner, via embedding-based matching of user queries and graph annotations, as \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mwell as the possibility of hybrid RAG schemes that combine embedding-based matching against community reports \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mbefore employing our map-reduce summarization mechanisms. This 'roll-up' operation could also be extended \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31macross more levels of the community hierarchy, as well as implemented as a more exploratory 'drill down' \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mmechanism that follows the information scent contained in higher-level community summaries.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m---\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mAdvanced RAG systems include pre-retrieval, retrieval, post-retrieval strategies designed to overcome the \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mdrawbacks of Naยจฤฑve RAG, while Modular RAG systems include patterns for iterative and dynamic cycles of \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31minterleaved retrieval and generation (Gao et al., 2023). Our implementation of Graph RAG incorporates multiple \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mconcepts related to other systems. For example, our community summaries are a kind of self-memory (Selfmem, \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mCheng et al., 2024) for generation-augmented retrieval (GAR, Mao et al., 2020) that facilitates future \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mgeneration cycles, while our parallel generation of community answers from these summaries is a kind of \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31miterative (Iter-RetGen, Shao et al., 2023) or federated (FeB4RAG, Wang et al., 2024) retrieval-generation \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mstrategy. Other systems have also combined these concepts for multi-document summarization (CAiRE-COVID, Su et \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mal., 2020) and multi-hop question answering (ITRG, Feng et al., 2023; IR-CoT, Trivedi et al., 2022; DSP, \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mKhattab et al., 2022). Our use of a hierarchical index and summarization also bears resemblance to further \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mapproaches, such as generating a hierarchical index of text chunks by clustering the vectors of text embeddings\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m(RAPTOR, Sarthi et al., 2024) or generating a 'tree of clarifications' to answer multiple interpretations of \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mambiguous questions (Kim et al., 2023). However, none of these iterative or hierarchical approaches use the \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mkind of self-generated graph index that enables Graph RAG.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m---\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mThe use of retrieval-augmented generation (RAG) to retrieve relevant information from an external knowledge \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31msource enables large language models (LLMs) to answer questions over private and/or previously unseen document \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mcollections. However, RAG fails on global questions directed at an entire text corpus, such as 'What are the \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mmain themes in the dataset?', since this is inherently a queryfocused summarization (QFS) task, rather than an \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mexplicit retrieval task. Prior QFS methods, meanwhile, fail to scale to the quantities of text indexed by \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mtypical RAGsystems. To combine the strengths of these contrasting methods, we propose a Graph RAG approach to \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mquestion answering over private text corpora that scales with both the generality of user questions and the \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mquantity of source text to be indexed. Our approach uses an LLM to build a graph-based text index in two \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mstages: first to derive an entity knowledge graph from the source documents, then to pregenerate community \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31msummaries for all groups of closely-related entities. Given a question, each community summary is used to \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mgenerate a partial response, before all partial responses are again summarized in a final response to the user.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mFor a class of global sensemaking questions over datasets in the 1 million token range, we show that Graph RAG \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mleads to substantial improvements over a naยจฤฑve RAG baseline for both the comprehensiveness and diversity of \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mgenerated answers. An open-source, Python-based implementation of both global and local Graph RAG approaches is\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mforthcoming at https://aka . ms/graphrag .\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m---\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mGiven the multi-stage nature of our Graph RAG mechanism, the multiple conditions we wanted to compare, and the \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mlack of gold standard answers to our activity-based sensemaking questions, we decided to adopt a head-to-head \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mcomparison approach using an LLM evaluator. We selected three target metrics capturing qualities that are \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mdesirable for sensemaking activities, as well as a control metric (directness) used as a indicator of validity.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mSince directness is effectively in opposition to comprehensiveness and diversity, we would not expect any \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mmethod to win across all four metrics.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m---\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mFigure 1: Graph RAG pipeline using an LLM-derived graph index of source document text. This index spans nodes \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m(e.g., entities), edges (e.g., relationships), and covariates (e.g., claims) that have been detected, \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mextracted, and summarized by LLM prompts tailored to the domain of the dataset. Community detection (e.g., \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mLeiden, Traag et al., 2019) is used to partition the graph index into groups of elements (nodes, edges, \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mcovariates) that the LLM can summarize in parallel at both indexing time and query time. The 'global answer' to\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31ma given query is produced using a final round of query-focused summarization over all community summaries \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mreporting relevance to that query.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m---\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mRetrieval-augmented generation (RAG, Lewis et al., 2020) is an established approach to answering user questions\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mover entire datasets, but it is designed for situations where these answers are contained locally within \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mregions of text whose retrieval provides sufficient grounding for the generation task. Instead, a more \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mappropriate task framing is query-focused summarization (QFS, Dang, 2006), and in particular, query-focused \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mabstractive summarization that generates natural language summaries and not just concatenated excerpts (Baumel \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31met al., 2018; Laskar et al., 2020; Yao et al., 2017) . In recent years, however, such distinctions between \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31msummarization tasks that are abstractive versus extractive, generic versus query-focused, and single-document \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mversus multi-document, have become less relevant. While early applications of the transformer architecture \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mshowed substantial improvements on the state-of-the-art for all such summarization tasks (Goodwin et al., 2020;\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mLaskar et al., 2022; Liu and Lapata, 2019), these tasks are now trivialized by modern LLMs, including the GPT \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m(Achiam et al., 2023; Brown et al., 2020), Llama (Touvron et al., 2023), and Gemini (Anil et al., 2023) series,\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mall of which can use in-context learning to summarize any content provided in their context window.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m---\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mcommunity descriptions provide complete coverage of the underlying graph index and the input documents it \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mrepresents. Query-focused summarization of an entire corpus is then made possible using a map-reduce approach: \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mfirst using each community summary to answer the query independently and in parallel, then summarizing all \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mrelevant partial answers into a final global answer.\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mQuestion: What are the main advantages of using the Graph RAG approach for query-focused summarization compared\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mto traditional RAG methods?\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mAnswer:\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโ\u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31m \u001b[0m\u001b[1;31mโ\u001b[0m\n",
"\u001b[1;31mโฐโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฏ\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"โญโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ RAG Response โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฎ\n",
"โ The main advantages of using the Graph RAG approach for query-focused summarization compared to traditional RAG โ\n",
"โ methods include: โ\n",
"โ โ\n",
"โ 1. **Improved Comprehensiveness and Diversity**: Graph RAG shows substantial improvements over a naรฏve RAG โ\n",
"โ baseline in terms of the comprehensiveness and diversity of answers. This is particularly beneficial for global โ\n",
"โ sensemaking questions over large datasets. โ\n",
"โ โ\n",
"โ 2. **Scalability**: Graph RAG provides scalability advantages, achieving efficient summarization with โ\n",
"โ significantly fewer context tokens required. For instance, it requires 26-33% fewer tokens for low-level โ\n",
"โ community summaries and over 97% fewer tokens for root-level summaries compared to source text summarization. โ\n",
"โ โ\n",
"โ 3. **Efficiency in Iterative Question Answering**: Root-level Graph RAG offers a highly efficient method for โ\n",
"โ iterative question answering, which is crucial for sensemaking activities, with only a modest drop in โ\n",
"โ performance compared to other global methods. โ\n",
"โ โ\n",
"โ 4. **Global Query Handling**: It supports handling global queries effectively, as it combines knowledge graph โ\n",
"โ generation, retrieval-augmented generation, and query-focused summarization, making it suitable for sensemaking โ\n",
"โ over entire text corpora. โ\n",
"โ โ\n",
"โ 5. **Hierarchical Indexing and Summarization**: The use of a hierarchical index and summarization allows for โ\n",
"โ efficient processing and summarizing of community summaries into a final global answer, facilitating a โ\n",
"โ comprehensive coverage of the underlying graph index and input documents. โ\n",
"โ โ\n",
"โ 6. **Reduced Token Cost**: For situations requiring many global queries over the same dataset, Graph RAG โ\n",
"โ achieves competitive performance to other global methods at a fraction of the token cost. โ\n",
"โฐโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฏ\n",
"\n"
],
"text/plain": [
"\u001b[1;32mโญโ\u001b[0m\u001b[1;32mโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ\u001b[0m RAG Response \u001b[1;32mโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ\u001b[0m\u001b[1;32mโโฎ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mThe main advantages of using the Graph RAG approach for query-focused summarization compared to traditional RAG\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mmethods include:\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m1. **Improved Comprehensiveness and Diversity**: Graph RAG shows substantial improvements over a naรฏve RAG \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mbaseline in terms of the comprehensiveness and diversity of answers. This is particularly beneficial for global\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32msensemaking questions over large datasets.\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m2. **Scalability**: Graph RAG provides scalability advantages, achieving efficient summarization with \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32msignificantly fewer context tokens required. For instance, it requires 26-33% fewer tokens for low-level \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mcommunity summaries and over 97% fewer tokens for root-level summaries compared to source text summarization.\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m3. **Efficiency in Iterative Question Answering**: Root-level Graph RAG offers a highly efficient method for \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32miterative question answering, which is crucial for sensemaking activities, with only a modest drop in \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mperformance compared to other global methods.\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m4. **Global Query Handling**: It supports handling global queries effectively, as it combines knowledge graph \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mgeneration, retrieval-augmented generation, and query-focused summarization, making it suitable for sensemaking\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mover entire text corpora.\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m5. **Hierarchical Indexing and Summarization**: The use of a hierarchical index and summarization allows for \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mefficient processing and summarizing of community summaries into a final global answer, facilitating a \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mcomprehensive coverage of the underlying graph index and input documents.\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m6. **Reduced Token Cost**: For situations requiring many global queries over the same dataset, Graph RAG \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโ\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32machieves competitive performance to other global methods at a fraction of the token cost.\u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32m \u001b[0m\u001b[1;32mโ\u001b[0m\n",
"\u001b[1;32mโฐโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฏ\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from typing import Optional\n",
"\n",
"from azure.search.documents.models import VectorizableTextQuery\n",
"\n",
"\n",
"def generate_chat_response(prompt: str, system_message: Optional[str] = None):\n",
" \"\"\"\n",
" Generates a single-turn chat response using Azure OpenAI Chat.\n",
" If you need multi-turn conversation or follow-up queries, you'll have to\n",
" maintain the messages list externally.\n",
" \"\"\"\n",
" messages = []\n",
" if system_message:\n",
" messages.append({\"role\": \"system\", \"content\": system_message})\n",
" messages.append({\"role\": \"user\", \"content\": prompt})\n",
"\n",
" completion = openai_client.chat.completions.create(\n",
" model=AZURE_OPENAI_CHAT_MODEL, messages=messages, temperature=0.7\n",
" )\n",
" return completion.choices[0].message.content\n",
"\n",
"\n",
"user_query = \"What are the main advantages of using the Graph RAG approach for query-focused summarization compared to traditional RAG methods?\"\n",
"user_embed = embed_text(user_query)\n",
"\n",
"vector_query = VectorizableTextQuery(\n",
" text=user_query, # passing in text for a hybrid search\n",
" k_nearest_neighbors=5,\n",
" fields=\"content_vector\",\n",
")\n",
"\n",
"search_results = search_client.search(\n",
" search_text=user_query, vector_queries=[vector_query], select=[\"content\"], top=10\n",
")\n",
"\n",
"retrieved_chunks = []\n",
"for result in search_results:\n",
" snippet = result[\"content\"]\n",
" retrieved_chunks.append(snippet)\n",
"\n",
"context_str = \"\\n---\\n\".join(retrieved_chunks)\n",
"rag_prompt = f\"\"\"\n",
"You are an AI assistant helping answering questions about Microsoft GraphRAG.\n",
"Use ONLY the text below to answer the user's question.\n",
"If the answer isn't in the text, say you don't know.\n",
"\n",
"Context:\n",
"{context_str}\n",
"\n",
"Question: {user_query}\n",
"Answer:\n",
"\"\"\"\n",
"\n",
"final_answer = generate_chat_response(rag_prompt)\n",
"\n",
"console.print(Panel(rag_prompt, title=\"RAG Prompt\", style=\"bold red\"))\n",
"console.print(Panel(final_answer, title=\"RAG Response\", style=\"bold green\"))"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": []
},
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.8"
}
},
"nbformat": 4,
"nbformat_minor": 0
}