yujunjun/graphrag
1
0
Fork 0
mirror of https://github.com/microsoft/graphrag.git synced 2025-12-29 16:09:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix styling and misalignment on drift docs (#1373)

Browse Source
This commit is contained in:
Alonso Guevara 2024-11-06 16:29:53 -06:00 committed by GitHub
parent 0394b55086
commit 2047c1561c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 22 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
docs/blog_posts.md
View File

@ -1,35 +1,34 @@
<div class="grid cards" markdown>
- [:octicons-arrow-right-24: **GraphRAG: Unlocking LLM discovery on narrative private data**](https://www.microsoft.com/en-us/research/blog/graphrag-unlocking-llm-discovery-on-narrative-private-data/)
- [:octicons-arrow-right-24: __GraphRAG: Unlocking LLM discovery on narrative private data__](https://www.microsoft.com/en-us/research/blog/graphrag-unlocking-llm-discovery-on-narrative-private-data/)
***
---
<h6>Published February 13, 2024
<h6>Published February 13, 2024
By [Jonathan Larson](https://www.microsoft.com/en-us/research/people/jolarso/), Senior Principal Data Architect; [Steven Truitt](https://www.microsoft.com/en-us/research/people/steventruitt/), Principal Program Manager</h6>
By [Jonathan Larson](https://www.microsoft.com/en-us/research/people/jolarso/), Senior Principal Data Architect; [Steven Truitt](https://www.microsoft.com/en-us/research/people/steventruitt/), Principal Program Manager</h6>
- [:octicons-arrow-right-24: __GraphRAG: New tool for complex data discovery now on GitHub__](https://www.microsoft.com/en-us/research/blog/graphrag-new-tool-for-complex-data-discovery-now-on-github/)
- [:octicons-arrow-right-24: **GraphRAG: New tool for complex data discovery now on GitHub**](https://www.microsoft.com/en-us/research/blog/graphrag-new-tool-for-complex-data-discovery-now-on-github/)
---
<h6>Published July 2, 2024
***
By [Darren Edge](https://www.microsoft.com/en-us/research/people/daedge/), Senior Director; [Ha Trinh](https://www.microsoft.com/en-us/research/people/trinhha/), Senior Data Scientist; [Steven Truitt](https://www.microsoft.com/en-us/research/people/steventruitt/), Principal Program Manager; [Jonathan Larson](https://www.microsoft.com/en-us/research/people/jolarso/), Senior Principal Data Architect</h6>
<h6>Published July 2, 2024
By [Darren Edge](https://www.microsoft.com/en-us/research/people/daedge/), Senior Director; [Ha Trinh](https://www.microsoft.com/en-us/research/people/trinhha/), Senior Data Scientist; [Steven Truitt](https://www.microsoft.com/en-us/research/people/steventruitt/), Principal Program Manager; [Jonathan Larson](https://www.microsoft.com/en-us/research/people/jolarso/), Senior Principal Data Architect</h6>
- [:octicons-arrow-right-24: __GraphRAG auto-tuning provides rapid adaptation to new domains__](https://www.microsoft.com/en-us/research/blog/graphrag-auto-tuning-provides-rapid-adaptation-to-new-domains/)
- [:octicons-arrow-right-24: **GraphRAG auto-tuning provides rapid adaptation to new domains**](https://www.microsoft.com/en-us/research/blog/graphrag-auto-tuning-provides-rapid-adaptation-to-new-domains/)
---
<h6>Published September 9, 2024
***
By [Alonso Guevara Fernández](https://www.microsoft.com/en-us/research/people/alonsog/), Sr. Software Engineer; Katy Smith, Data Scientist II; [Joshua Bradley](https://www.microsoft.com/en-us/research/people/joshbradley/), Senior Data Scientist; [Darren Edge](https://www.microsoft.com/en-us/research/people/daedge/), Senior Director; [Ha Trinh](https://www.microsoft.com/en-us/research/people/trinhha/), Senior Data Scientist; [Sarah Smith](https://www.microsoft.com/en-us/research/people/smithsarah/), Senior Program Manager; [Ben Cutler](https://www.microsoft.com/en-us/research/people/bcutler/), Senior Director; [Steven Truitt](https://www.microsoft.com/en-us/research/people/steventruitt/), Principal Program Manager; [Jonathan Larson](https://www.microsoft.com/en-us/research/people/jolarso/), Senior Principal Data Architect</h6>
<h6>Published September 9, 2024
- [:octicons-arrow-right-24: __Introducing DRIFT Search: Combining global and local search methods to improve quality and efficiency__](https://www.microsoft.com/en-us/research/blog/introducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiency/)
By [Alonso Guevara Fernández](https://www.microsoft.com/en-us/research/people/alonsog/), Sr. Software Engineer; Katy Smith, Data Scientist II; [Joshua Bradley](https://www.microsoft.com/en-us/research/people/joshbradley/), Senior Data Scientist; [Darren Edge](https://www.microsoft.com/en-us/research/people/daedge/), Senior Director; [Ha Trinh](https://www.microsoft.com/en-us/research/people/trinhha/), Senior Data Scientist; [Sarah Smith](https://www.microsoft.com/en-us/research/people/smithsarah/), Senior Program Manager; [Ben Cutler](https://www.microsoft.com/en-us/research/people/bcutler/), Senior Director; [Steven Truitt](https://www.microsoft.com/en-us/research/people/steventruitt/), Principal Program Manager; [Jonathan Larson](https://www.microsoft.com/en-us/research/people/jolarso/), Senior Principal Data Architect
---
<h6>Published October 31, 2024
- [:octicons-arrow-right-24: **Introducing DRIFT Search: Combining global and local search methods to improve quality and efficiency**](https://www.microsoft.com/en-us/research/blog/introducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiency/)
By Julian Whiting, Senior Machine Learning Engineer; Zachary Hills , Senior Software Engineer; [Alonso Guevara Fernández](https://www.microsoft.com/en-us/research/people/alonsog/), Sr. Software Engineer; [Ha Trinh](https://www.microsoft.com/en-us/research/people/trinhha/), Senior Data Scientist; Adam Bradley , Managing Partner, Strategic Research; [Jonathan Larson](https://www.microsoft.com/en-us/research/people/jolarso/), Senior Principal Data Architect</h6>
***
<h6>Published October 31, 2024
By Julian Whiting , Senior Machine Learning Engineer; Zachary Hills , Senior Software Engineer; [Alonso Guevara Fernández](https://www.microsoft.com/en-us/research/people/alonsog/), Sr. Software Engineer; [Ha Trinh](https://www.microsoft.com/en-us/research/people/trinhha/), Senior Data Scientist; Adam Bradley , Managing Partner, Strategic Research; [Jonathan Larson](https://www.microsoft.com/en-us/research/people/jolarso/), Senior Principal Data Architect
</div>
</div>

6
docs/query/drift_search.md
View File

@ -11,9 +11,9 @@ DRIFT search (Dynamic Reasoning and Inference with Flexible Traversal) builds up
<p align="center">
<img src="../../img/drift-search-diagram.png" alt="Figure 1. An entire DRIFT search hierarchy highlighting the three core phases of the DRIFT search process." align="center" />
</p>
<p align="center"><i>
Figure 1. An entire DRIFT search hierarchy highlighting the three core phases of the DRIFT search process. A (Primer): DRIFT compares the user’s query with the top K most semantically relevant community reports, generating a broad initial answer and follow-up questions to steer further exploration. B (Follow-Up): DRIFT uses local search to refine queries, producing additional intermediate answers and follow-up questions that enhance specificity, guiding the engine towards context-rich information. A glyph on each node in the diagram shows the confidence the algorithm has to continue the query expansion step. C (Output Hierarchy): The final output is a hierarchical structure of questions and answers ranked by relevance, reflecting a balanced mix of global insights and local refinements, making the results adaptable and comprehensive.</i></p>
<p align="center">
<p align="center"><i><small>
Figure 1. An entire DRIFT search hierarchy highlighting the three core phases of the DRIFT search process. A (Primer): DRIFT compares the user’s query with the top K most semantically relevant community reports, generating a broad initial answer and follow-up questions to steer further exploration. B (Follow-Up): DRIFT uses local search to refine queries, producing additional intermediate answers and follow-up questions that enhance specificity, guiding the engine towards context-rich information. A glyph on each node in the diagram shows the confidence the algorithm has to continue the query expansion step. C (Output Hierarchy): The final output is a hierarchical structure of questions and answers ranked by relevance, reflecting a balanced mix of global insights and local refinements, making the results adaptable and comprehensive.</small></i></p>
DRIFT Search introduces a new approach to local search queries by including community information in the search process. This greatly expands the breadth of the query’s starting point and leads to retrieval and usage of a far higher variety of facts in the final answer. This addition expands the GraphRAG query engine by providing a more comprehensive option for local search, which uses community insights to refine a query into detailed follow-up questions.