From 4d32022cc82936eaf14d7a97c7173e9b39339b92 Mon Sep 17 00:00:00 2001 From: AlonsoGuevara Date: Thu, 5 Dec 2024 22:16:12 +0000 Subject: [PATCH] =?UTF-8?q?Deploying=20to=20gh-pages=20from=20@=20microsof?= =?UTF-8?q?t/graphrag@d17dfd01f906b7aaa6506367aee76752c768b473=20?= =?UTF-8?q?=F0=9F=9A=80?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- config/yaml/index.html | 2 - examples_notebooks/drift_search/index.html | 3832 +---------------- examples_notebooks/global_search/index.html | 196 +- .../index.html | 430 +- examples_notebooks/local_search/index.html | 634 +-- search/search_index.json | 2 +- sitemap.xml.gz | Bin 127 -> 127 bytes 7 files changed, 1057 insertions(+), 4039 deletions(-) diff --git a/config/yaml/index.html b/config/yaml/index.html index c11bd831..19e1e00c 100644 --- a/config/yaml/index.html +++ b/config/yaml/index.html @@ -1590,8 +1590,6 @@

encoding_model

diff --git a/examples_notebooks/drift_search/index.html b/examples_notebooks/drift_search/index.html index 70d1ad36..0bb2efcd 100644 --- a/examples_notebooks/drift_search/index.html +++ b/examples_notebooks/drift_search/index.html @@ -2015,7 +2015,7 @@ Text unit records: 50
@@ -2287,15 +2287,130 @@ reports = read_indexer_reports(
+
+ +
-
- +
+
+
+
+ + +
@@ -2752,3316 +2564,16 @@ search = DRIFTSearch(
@@ -3409,26 +3495,113 @@ print(result.response)
+
+ + +
@@ -3473,78 +3646,16 @@ In summary, Dr. Jordan Hayes is a vital asset to the Paranormal Military Squad,
-
@@ -3580,97 +3691,23 @@ In summary, Dr. Jordan Hayes is a vital asset to the Paranormal Military Squad,
-
- -
- +
+
diff --git a/search/search_index.json b/search/search_index.json index ca6ec13e..e9b33690 100644 --- a/search/search_index.json +++ b/search/search_index.json @@ -1 +1 @@ -{"config": {"lang": ["en"], "separator": "[\\s\\-]+", "pipeline": ["stopWordFilter"]}, "docs": [{"location": "", "title": "Welcome to GraphRAG", "text": "

\ud83d\udc49 Microsoft Research Blog Post \ud83d\udc49 GraphRAG Accelerator \ud83d\udc49 GraphRAG Arxiv

Figure 1: An LLM-generated knowledge graph built using GPT-4 Turbo.

GraphRAG is a structured, hierarchical approach to Retrieval Augmented Generation (RAG), as opposed to naive semantic-search approaches using plain text snippets. The GraphRAG process involves extracting a knowledge graph out of raw text, building a community hierarchy, generating summaries for these communities, and then leveraging these structures when perform RAG-based tasks.

To learn more about GraphRAG and how it can be used to enhance your LLMs ability to reason about your private data, please visit the Microsoft Research Blog Post.

"}, {"location": "#solution-accelerator", "title": "Solution Accelerator \ud83d\ude80", "text": "

To quickstart the GraphRAG system we recommend trying the Solution Accelerator package. This provides a user-friendly end-to-end experience with Azure resources.

"}, {"location": "#get-started-with-graphrag", "title": "Get Started with GraphRAG \ud83d\ude80", "text": "

To start using GraphRAG, check out the Get Started guide. For a deeper dive into the main sub-systems, please visit the docpages for the Indexer and Query packages.

"}, {"location": "#graphrag-vs-baseline-rag", "title": "GraphRAG vs Baseline RAG \ud83d\udd0d", "text": "

Retrieval-Augmented Generation (RAG) is a technique to improve LLM outputs using real-world information. This technique is an important part of most LLM-based tools and the majority of RAG approaches use vector similarity as the search technique, which we call Baseline RAG. GraphRAG uses knowledge graphs to provide substantial improvements in question-and-answer performance when reasoning about complex information. RAG techniques have shown promise in helping LLMs to reason about private datasets - data that the LLM is not trained on and has never seen before, such as an enterprise\u2019s proprietary research, business documents, or communications. Baseline RAG was created to help solve this problem, but we observe situations where baseline RAG performs very poorly. For example:

To address this, the tech community is working to develop methods that extend and enhance RAG. Microsoft Research\u2019s new approach, GraphRAG, uses LLMs to create a knowledge graph based on an input corpus. This graph, along with community summaries and graph machine learning outputs, are used to augment prompts at query time. GraphRAG shows substantial improvement in answering the two classes of questions described above, demonstrating intelligence or mastery that outperforms other approaches previously applied to private datasets.

"}, {"location": "#the-graphrag-process", "title": "The GraphRAG Process \ud83e\udd16", "text": "

GraphRAG builds upon our prior research and tooling using graph machine learning. The basic steps of the GraphRAG process are as follows:

"}, {"location": "#index", "title": "Index", "text": ""}, {"location": "#query", "title": "Query", "text": "

At query time, these structures are used to provide materials for the LLM context window when answering a question. The primary query modes are:

"}, {"location": "#prompt-tuning", "title": "Prompt Tuning", "text": "

Using GraphRAG with your data out of the box may not yield the best possible results. We strongly recommend to fine-tune your prompts following the Prompt Tuning Guide in our documentation.

"}, {"location": "blog_posts/", "title": "Microsoft Research Blog", "text": "