mirror of
https://github.com/microsoft/graphrag.git
synced 2025-09-08 15:56:21 +00:00
Deploying to gh-pages from @ microsoft/graphrag@2047c1561c 🚀
This commit is contained in:
AlonsoGuevara
parent
3478362f42
commit
fd7de76a9c
@ -75,11 +75,6 @@
|
||||
<label class="md-overlay" for="__drawer"></label>
|
||||
<div data-md-component="skip">
|
||||
|
||||
|
||||
<a href="#published-february-13-2024-by-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect-steven-truitthttpswwwmicrosoftcomen-usresearchpeoplesteventruitt-principal-program-manager" class="md-skip">
|
||||
Skip to content
|
||||
</a>
|
||||
|
||||
</div>
|
||||
<div data-md-component="announce">
|
||||
|
||||
@ -1156,17 +1151,6 @@
|
||||
|
||||
|
||||
|
||||
<label class="md-nav__link md-nav__link--active" for="__toc">
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Microsoft Research Blog
|
||||
</span>
|
||||
|
||||
|
||||
<span class="md-nav__icon md-icon"></span>
|
||||
</label>
|
||||
|
||||
<a href="./" class="md-nav__link md-nav__link--active">
|
||||
|
||||
|
||||
@ -1177,59 +1161,6 @@
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
|
||||
|
||||
|
||||
|
||||
|
||||
<label class="md-nav__title" for="__toc">
|
||||
<span class="md-nav__icon md-icon"></span>
|
||||
Table of contents
|
||||
</label>
|
||||
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#published-february-13-2024-by-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect-steven-truitthttpswwwmicrosoftcomen-usresearchpeoplesteventruitt-principal-program-manager" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
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
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#published-july-2-2024-by-darren-edgehttpswwwmicrosoftcomen-usresearchpeopledaedge-senior-director-ha-trinhhttpswwwmicrosoftcomen-usresearchpeopletrinhha-senior-data-scientist-steven-truitthttpswwwmicrosoftcomen-usresearchpeoplesteventruitt-principal-program-manager-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
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
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#published-september-9-2024-by-alonso-guevara-fernandezhttpswwwmicrosoftcomen-usresearchpeoplealonsog-sr-software-engineer-katy-smith-data-scientist-ii-joshua-bradleyhttpswwwmicrosoftcomen-usresearchpeoplejoshbradley-senior-data-scientist-darren-edgehttpswwwmicrosoftcomen-usresearchpeopledaedge-senior-director-ha-trinhhttpswwwmicrosoftcomen-usresearchpeopletrinhha-senior-data-scientist-sarah-smithhttpswwwmicrosoftcomen-usresearchpeoplesmithsarah-senior-program-manager-ben-cutlerhttpswwwmicrosoftcomen-usresearchpeoplebcutler-senior-director-steven-truitthttpswwwmicrosoftcomen-usresearchpeoplesteventruitt-principal-program-manager-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect-octicons-arrow-right-24-introducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiencyhttpswwwmicrosoftcomen-usresearchblogintroducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiency-published-october-31-2024-by-julian-whiting-senior-machine-learning-engineer-zachary-hills-senior-software-engineer-alonso-guevara-fernandezhttpswwwmicrosoftcomen-usresearchpeoplealonsog-sr-software-engineer-ha-trinhhttpswwwmicrosoftcomen-usresearchpeopletrinhha-senior-data-scientist-adam-bradley-managing-partner-strategic-research-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
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 - [: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/) *** 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
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#published-october-31-2024-by-julian-whiting-senior-machine-learning-engineer-zachary-hills-senior-software-engineer-alonso-guevara-fernandezhttpswwwmicrosoftcomen-usresearchpeoplealonsog-sr-software-engineer-ha-trinhhttpswwwmicrosoftcomen-usresearchpeopletrinhha-senior-data-scientist-adam-bradley-managing-partner-strategic-research-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
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
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
@ -1427,50 +1358,6 @@
|
||||
|
||||
|
||||
|
||||
<label class="md-nav__title" for="__toc">
|
||||
<span class="md-nav__icon md-icon"></span>
|
||||
Table of contents
|
||||
</label>
|
||||
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#published-february-13-2024-by-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect-steven-truitthttpswwwmicrosoftcomen-usresearchpeoplesteventruitt-principal-program-manager" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
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
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#published-july-2-2024-by-darren-edgehttpswwwmicrosoftcomen-usresearchpeopledaedge-senior-director-ha-trinhhttpswwwmicrosoftcomen-usresearchpeopletrinhha-senior-data-scientist-steven-truitthttpswwwmicrosoftcomen-usresearchpeoplesteventruitt-principal-program-manager-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
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
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#published-september-9-2024-by-alonso-guevara-fernandezhttpswwwmicrosoftcomen-usresearchpeoplealonsog-sr-software-engineer-katy-smith-data-scientist-ii-joshua-bradleyhttpswwwmicrosoftcomen-usresearchpeoplejoshbradley-senior-data-scientist-darren-edgehttpswwwmicrosoftcomen-usresearchpeopledaedge-senior-director-ha-trinhhttpswwwmicrosoftcomen-usresearchpeopletrinhha-senior-data-scientist-sarah-smithhttpswwwmicrosoftcomen-usresearchpeoplesmithsarah-senior-program-manager-ben-cutlerhttpswwwmicrosoftcomen-usresearchpeoplebcutler-senior-director-steven-truitthttpswwwmicrosoftcomen-usresearchpeoplesteventruitt-principal-program-manager-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect-octicons-arrow-right-24-introducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiencyhttpswwwmicrosoftcomen-usresearchblogintroducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiency-published-october-31-2024-by-julian-whiting-senior-machine-learning-engineer-zachary-hills-senior-software-engineer-alonso-guevara-fernandezhttpswwwmicrosoftcomen-usresearchpeoplealonsog-sr-software-engineer-ha-trinhhttpswwwmicrosoftcomen-usresearchpeopletrinhha-senior-data-scientist-adam-bradley-managing-partner-strategic-research-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
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 - [: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/) *** 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
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#published-october-31-2024-by-julian-whiting-senior-machine-learning-engineer-zachary-hills-senior-software-engineer-alonso-guevara-fernandezhttpswwwmicrosoftcomen-usresearchpeoplealonsog-sr-software-engineer-ha-trinhhttpswwwmicrosoftcomen-usresearchpeopletrinhha-senior-data-scientist-adam-bradley-managing-partner-strategic-research-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
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
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
</nav>
|
||||
</div>
|
||||
</div>
|
||||
@ -1491,37 +1378,31 @@
|
||||
|
||||
<div class="grid cards">
|
||||
<ul>
|
||||
<li><a href="https://www.microsoft.com/en-us/research/blog/graphrag-unlocking-llm-discovery-on-narrative-private-data/"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> <strong>GraphRAG: Unlocking LLM discovery on narrative private data</strong></a></li>
|
||||
</ul>
|
||||
<li>
|
||||
<p><a href="https://www.microsoft.com/en-us/research/blog/graphrag-unlocking-llm-discovery-on-narrative-private-data/"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> <strong>GraphRAG: Unlocking LLM discovery on narrative private data</strong></a></p>
|
||||
<hr />
|
||||
<h6 id="published-february-13-2024-by-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect-steven-truitthttpswwwmicrosoftcomen-usresearchpeoplesteventruitt-principal-program-manager">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>
|
||||
<ul>
|
||||
<li><a href="https://www.microsoft.com/en-us/research/blog/graphrag-new-tool-for-complex-data-discovery-now-on-github/"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> <strong>GraphRAG: New tool for complex data discovery now on GitHub</strong></a></li>
|
||||
</ul>
|
||||
<p><h6>Published February 13, 2024</p>
|
||||
<p>By <a href="https://www.microsoft.com/en-us/research/people/jolarso/">Jonathan Larson</a>, Senior Principal Data Architect; <a href="https://www.microsoft.com/en-us/research/people/steventruitt/">Steven Truitt</a>, Principal Program Manager</h6></p>
|
||||
</li>
|
||||
<li>
|
||||
<p><a href="https://www.microsoft.com/en-us/research/blog/graphrag-new-tool-for-complex-data-discovery-now-on-github/"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> <strong>GraphRAG: New tool for complex data discovery now on GitHub</strong></a></p>
|
||||
<hr />
|
||||
<h6 id="published-july-2-2024-by-darren-edgehttpswwwmicrosoftcomen-usresearchpeopledaedge-senior-director-ha-trinhhttpswwwmicrosoftcomen-usresearchpeopletrinhha-senior-data-scientist-steven-truitthttpswwwmicrosoftcomen-usresearchpeoplesteventruitt-principal-program-manager-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect">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>
|
||||
<ul>
|
||||
<li><a href="https://www.microsoft.com/en-us/research/blog/graphrag-auto-tuning-provides-rapid-adaptation-to-new-domains/"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> <strong>GraphRAG auto-tuning provides rapid adaptation to new domains</strong></a></li>
|
||||
</ul>
|
||||
<p><h6>Published July 2, 2024</p>
|
||||
<p>By <a href="https://www.microsoft.com/en-us/research/people/daedge/">Darren Edge</a>, Senior Director; <a href="https://www.microsoft.com/en-us/research/people/trinhha/">Ha Trinh</a>, Senior Data Scientist; <a href="https://www.microsoft.com/en-us/research/people/steventruitt/">Steven Truitt</a>, Principal Program Manager; <a href="https://www.microsoft.com/en-us/research/people/jolarso/">Jonathan Larson</a>, Senior Principal Data Architect</h6></p>
|
||||
</li>
|
||||
<li>
|
||||
<p><a href="https://www.microsoft.com/en-us/research/blog/graphrag-auto-tuning-provides-rapid-adaptation-to-new-domains/"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> <strong>GraphRAG auto-tuning provides rapid adaptation to new domains</strong></a></p>
|
||||
<hr />
|
||||
<h6 id="published-september-9-2024-by-alonso-guevara-fernandezhttpswwwmicrosoftcomen-usresearchpeoplealonsog-sr-software-engineer-katy-smith-data-scientist-ii-joshua-bradleyhttpswwwmicrosoftcomen-usresearchpeoplejoshbradley-senior-data-scientist-darren-edgehttpswwwmicrosoftcomen-usresearchpeopledaedge-senior-director-ha-trinhhttpswwwmicrosoftcomen-usresearchpeopletrinhha-senior-data-scientist-sarah-smithhttpswwwmicrosoftcomen-usresearchpeoplesmithsarah-senior-program-manager-ben-cutlerhttpswwwmicrosoftcomen-usresearchpeoplebcutler-senior-director-steven-truitthttpswwwmicrosoftcomen-usresearchpeoplesteventruitt-principal-program-manager-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect-octicons-arrow-right-24-introducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiencyhttpswwwmicrosoftcomen-usresearchblogintroducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiency-published-october-31-2024-by-julian-whiting-senior-machine-learning-engineer-zachary-hills-senior-software-engineer-alonso-guevara-fernandezhttpswwwmicrosoftcomen-usresearchpeoplealonsog-sr-software-engineer-ha-trinhhttpswwwmicrosoftcomen-usresearchpeopletrinhha-senior-data-scientist-adam-bradley-managing-partner-strategic-research-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect">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
|
||||
|
||||
- [: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/)
|
||||
|
||||
***
|
||||
|
||||
<h6 id="published-october-31-2024-by-julian-whiting-senior-machine-learning-engineer-zachary-hills-senior-software-engineer-alonso-guevara-fernandezhttpswwwmicrosoftcomen-usresearchpeoplealonsog-sr-software-engineer-ha-trinhhttpswwwmicrosoftcomen-usresearchpeopletrinhha-senior-data-scientist-adam-bradley-managing-partner-strategic-research-jonathan-larsonhttpswwwmicrosoftcomen-usresearchpeoplejolarso-senior-principal-data-architect">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
|
||||
|
||||
</h6>
|
||||
</h6>
|
||||
<p><h6>Published September 9, 2024</p>
|
||||
<p>By <a href="https://www.microsoft.com/en-us/research/people/alonsog/">Alonso Guevara Fernández</a>, Sr. Software Engineer; Katy Smith, Data Scientist II; <a href="https://www.microsoft.com/en-us/research/people/joshbradley/">Joshua Bradley</a>, Senior Data Scientist; <a href="https://www.microsoft.com/en-us/research/people/daedge/">Darren Edge</a>, Senior Director; <a href="https://www.microsoft.com/en-us/research/people/trinhha/">Ha Trinh</a>, Senior Data Scientist; <a href="https://www.microsoft.com/en-us/research/people/smithsarah/">Sarah Smith</a>, Senior Program Manager; <a href="https://www.microsoft.com/en-us/research/people/bcutler/">Ben Cutler</a>, Senior Director; <a href="https://www.microsoft.com/en-us/research/people/steventruitt/">Steven Truitt</a>, Principal Program Manager; <a href="https://www.microsoft.com/en-us/research/people/jolarso/">Jonathan Larson</a>, Senior Principal Data Architect</h6></p>
|
||||
</li>
|
||||
<li>
|
||||
<p><a href="https://www.microsoft.com/en-us/research/blog/introducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiency/"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13.22 19.03a.75.75 0 0 1 0-1.06L18.19 13H3.75a.75.75 0 0 1 0-1.5h14.44l-4.97-4.97a.749.749 0 0 1 .326-1.275.75.75 0 0 1 .734.215l6.25 6.25a.75.75 0 0 1 0 1.06l-6.25 6.25a.75.75 0 0 1-1.06 0"/></svg></span> <strong>Introducing DRIFT Search: Combining global and local search methods to improve quality and efficiency</strong></a></p>
|
||||
<hr />
|
||||
<p><h6>Published October 31, 2024</p>
|
||||
<p>By Julian Whiting, Senior Machine Learning Engineer; Zachary Hills , Senior Software Engineer; <a href="https://www.microsoft.com/en-us/research/people/alonsog/">Alonso Guevara Fernández</a>, Sr. Software Engineer; <a href="https://www.microsoft.com/en-us/research/people/trinhha/">Ha Trinh</a>, Senior Data Scientist; Adam Bradley , Managing Partner, Strategic Research; <a href="https://www.microsoft.com/en-us/research/people/jolarso/">Jonathan Larson</a>, Senior Principal Data Architect</h6></p>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
File diff suppressed because one or more lines are too long
@ -2564,15 +2564,15 @@ print(result.response)</div>
|
||||
<div class="jp-RenderedText jp-OutputArea-output" data-mime-type="text/plain" tabindex="0">
|
||||
<pre>### Major Conflict
|
||||
|
||||
The central conflict in the story revolves around the Paranormal Military Squad's mission to establish contact with extraterrestrial intelligence. This involves deciphering alien signals and managing the potential implications of first contact. The mission is characterized by its secrecy and high stakes, as well as the challenges posed by the unknown nature of the extraterrestrial entities. The complexity of the situation is heightened by the need to understand and interpret signals from an entirely unfamiliar source, which could have significant consequences for humanity [Data: Reports (4, 5, 2, 3, 0)].
|
||||
The central conflict in the story revolves around the Paranormal Military Squad's mission to establish contact with extraterrestrial intelligence. This involves deciphering alien signals and managing the potential implications of first contact. The mission is characterized by its secrecy and high stakes, as well as the challenges posed by the unknown nature of the extraterrestrial entities. The squad must navigate these uncertainties and the potential risks associated with communicating with an unknown force [Data: Reports (4, 5, 2, 3, 0)].
|
||||
|
||||
### Protagonists
|
||||
|
||||
The protagonists are the key members of the Paranormal Military Squad, who play pivotal roles in the mission. This team includes Taylor Cruz, Dr. Jordan Hayes, Alex Mercer, and Sam Rivera. Each member contributes their unique expertise: Taylor Cruz provides leadership, Dr. Jordan Hayes focuses on signal decryption, Alex Mercer engages in diplomatic efforts, and Sam Rivera brings technical innovation to the team. Together, they work to navigate the complexities of the mission and ensure its success [Data: Reports (4, 5, 2, 3, 0)].
|
||||
The protagonists of the story are the members of the Paranormal Military Squad. Key figures include Taylor Cruz, Dr. Jordan Hayes, Alex Mercer, and Sam Rivera. These individuals play pivotal roles in the mission, contributing their expertise and leadership to achieve the squad's objectives. Their efforts are central to the narrative as they work together to overcome the challenges presented by the mission [Data: Reports (4, 5, 2, 3, 0)].
|
||||
|
||||
### Antagonist
|
||||
|
||||
In this narrative, there is no clear antagonist in the traditional sense. Instead, the conflict arises from the challenges and uncertainties associated with extraterrestrial communication. The antagonist role may be represented by the unknown and potentially threatening nature of the extraterrestrial signals and the implications of first contact. This abstract form of opposition underscores the tension and uncertainty inherent in the mission, as the team grapples with the unknown [Data: Reports (4, 5, 2, 3, 0)].
|
||||
There is no clear antagonist in the traditional sense within this story. The conflict primarily involves the challenges and uncertainties associated with extraterrestrial communication. The extraterrestrial entities themselves may be perceived as an unknown force that the squad must navigate, but they are not explicitly depicted as antagonists. Instead, the story focuses on the internal and external challenges faced by the protagonists as they engage with the unknown [Data: Reports (4, 5, 2, 3, 0)].
|
||||
</pre>
|
||||
</div>
|
||||
</div>
|
||||
@ -2723,7 +2723,7 @@ print(f"LLM calls: {result.llm_calls}. LLM tokens: {result.prompt_tokens}")</div
|
||||
<div class="jp-OutputArea-child">
|
||||
<div class="jp-OutputPrompt jp-OutputArea-prompt"></div>
|
||||
<div class="jp-RenderedText jp-OutputArea-output" data-mime-type="text/plain" tabindex="0">
|
||||
<pre>LLM calls: 2. LLM tokens: 5284
|
||||
<pre>LLM calls: 2. LLM tokens: 5280
|
||||
</pre>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@ -2380,7 +2380,7 @@ entity_df.head()</div>
|
||||
<div class="jp-OutputArea-child">
|
||||
<div class="jp-OutputPrompt jp-OutputArea-prompt"></div>
|
||||
<div class="jp-RenderedText jp-OutputArea-output" data-mime-type="application/vnd.jupyter.stderr" tabindex="0">
|
||||
<pre>[2024-11-06T19:22:42Z WARN lance::dataset] No existing dataset at /home/runner/work/graphrag/graphrag/docs/examples_notebooks/inputs/operation dulce/lancedb/entity.description.lance, it will be created
|
||||
<pre>[2024-11-06T22:33:22Z WARN lance::dataset] No existing dataset at /home/runner/work/graphrag/graphrag/docs/examples_notebooks/inputs/operation dulce/lancedb/entity.description.lance, it will be created
|
||||
</pre>
|
||||
</div>
|
||||
</div>
|
||||
@ -3368,25 +3368,21 @@ print(result.response)</div>
|
||||
<div class="jp-RenderedText jp-OutputArea-output" data-mime-type="text/plain" tabindex="0">
|
||||
<pre>### Overview of Agent Alex Mercer
|
||||
|
||||
Agent Alex Mercer is a central figure within the Paranormal Military Squad at Dulce Base, where he plays a pivotal role in overseeing operations and making critical decisions during potential first contact scenarios. His military background equips him with the necessary skills to lead his team effectively, particularly in the complex and high-stakes environment of interspecies communication and extraterrestrial intelligence engagement [Data: Entities (0, 209)].
|
||||
Agent Alex Mercer is a central figure within the Paranormal Military Squad at Dulce Base, where he plays a pivotal role in overseeing operations related to potential extraterrestrial contact. His responsibilities are multifaceted, encompassing leadership, strategic oversight, and direct involvement in interspecies communication efforts. Mercer's military background equips him with the skills necessary to guide his team through complex and potentially perilous scenarios, such as those encountered during Operation: Dulce [Data: Entities (0, 209, 143); Relationships (5, 8, 7)].
|
||||
|
||||
### Role and Responsibilities
|
||||
### Leadership and Collaboration
|
||||
|
||||
Mercer is deeply involved in the operational aspects of Dulce Base's command center, where he is responsible for guiding the team's response to extraterrestrial contact. His leadership is characterized by a cautious approach to interspecies communication, ensuring that any engagement with alien intelligence is handled with strategic foresight and care. This involves not only overseeing the team but also participating in decryption efforts and unraveling galactic mysteries [Data: Entities (0, 209); Relationships (5, 8, 7)].
|
||||
Mercer is recognized for his leadership within the Paranormal Military Squad, where he is instrumental in guiding the team, particularly in the realm of interspecies communication. His role involves spearheading efforts to engage with extraterrestrial intelligence, leveraging his military experience to enhance the mission's success. Mercer's leadership is characterized by a cautious and strategic approach, ensuring that the engagement with extraterrestrial intelligence is handled with care and foresight [Data: Entities (0, 209); Relationships (5, 6, 8)].
|
||||
|
||||
### Relationships and Team Dynamics
|
||||
### Key Relationships
|
||||
|
||||
Within the Paranormal Military Squad, Mercer collaborates closely with several key team members. He works alongside Dr. Jordan Hayes on decrypting and communicating with extraterrestrial intelligence, a partnership that is marked by mutual respect and recognition of each other's analytical skills [Data: Relationships (1, 4, 26, 67)]. Additionally, Mercer acts as a mentor to Sam Rivera, emphasizing the importance of intuition and trust in their mission [Data: Relationships (2, 37); Claims (8)].
|
||||
|
||||
### Leadership and Strategic Oversight
|
||||
|
||||
Mercer's leadership extends beyond tactical operations to include strategic oversight of the mission's progress. He is involved in discussions with Taylor Cruz, another integral member of the squad, where they focus on developing protocols for responding to alien communication. Despite some tension and authority dynamics between them, Mercer is recognized as the leader of the team, with Cruz providing strategic input [Data: Relationships (0, 18); Claims (9)].
|
||||
Agent Mercer works closely with several key members of the Paranormal Military Squad. He collaborates with Dr. Jordan Hayes on decrypting and communicating with extraterrestrial intelligence, a partnership that highlights their mutual respect and recognition of each other's analytical skills. Additionally, Mercer acts as a mentor to Sam Rivera, emphasizing the importance of intuition and trust in their mission. His interactions with Taylor Cruz, another integral member of the squad, involve strategic discussions, although there is a noted tension and authority dynamic between them [Data: Relationships (0, 1, 2, 4, 18); Claims (8, 9)].
|
||||
|
||||
### Involvement in Operation: Dulce
|
||||
|
||||
Agent Mercer is a key figure in Operation: Dulce, where he leads efforts to establish contact with extraterrestrial intelligence. His role involves interpreting alien messages and ensuring that the team's actions align with the broader objectives of their mission. Mercer's involvement in this operation highlights his commitment to understanding and engaging with the signals from beyond, positioning him as a representative of humanity in this unprecedented endeavor [Data: Relationships (6, 65); Claims (85, 82)].
|
||||
Agent Mercer is deeply involved in Operation: Dulce, where he leads his team in efforts to establish contact with extraterrestrial intelligence. His role in this operation is crucial, as he is responsible for guiding the team's response to extraterrestrial contact and ensuring that their efforts are aligned with the mission's objectives. Mercer's involvement in the decryption and analysis of alien signals further underscores his central role in the operation, contributing to the understanding of an extraterrestrial society [Data: Entities (0, 209); Relationships (7, 8, 6); Claims (73, 85, 82)].
|
||||
|
||||
In summary, Agent Alex Mercer is a highly skilled and experienced leader within the Paranormal Military Squad, whose efforts are crucial to the success of their mission at Dulce Base. His ability to navigate the complexities of extraterrestrial communication and his strategic oversight make him an indispensable asset to the team.
|
||||
In summary, Agent Alex Mercer is a key leader within the Paranormal Military Squad, whose expertise and strategic oversight are vital to the success of their mission at Dulce Base. His collaborative efforts with team members and his involvement in Operation: Dulce highlight his significant contributions to the field of interspecies communication and extraterrestrial intelligence.
|
||||
</pre>
|
||||
</div>
|
||||
</div>
|
||||
@ -3432,21 +3428,21 @@ print(result.response)</div>
|
||||
<div class="jp-RenderedText jp-OutputArea-output" data-mime-type="text/plain" tabindex="0">
|
||||
<pre>### Overview of Dr. Jordan Hayes
|
||||
|
||||
Dr. Jordan Hayes is a prominent figure within the Paranormal Military Squad, a specialized team stationed at Dulce Base, dedicated to the exploration and understanding of extraterrestrial intelligence and phenomena. Dr. Hayes plays a crucial role in the squad, focusing on deciphering alien code and interpreting extraterrestrial patterns. This expertise is vital to the squad's mission of understanding and interacting with extraterrestrial entities [Data: Entities (104, 2); Relationships (22, 40, 64)].
|
||||
Dr. Jordan Hayes is a prominent figure within the Paranormal Military Squad, a specialized team operating at the Dulce Base. Dr. Hayes plays a crucial role in the squad's mission to understand and communicate with extraterrestrial entities. Their expertise lies in deciphering alien code and interpreting extraterrestrial patterns, which are essential for the team's efforts in interspecies communication [Data: Entities (104, 2); Relationships (22, 40, 64)].
|
||||
|
||||
### Expertise and Contributions
|
||||
### Role and Expertise
|
||||
|
||||
Dr. Hayes is known for their analytical and skeptical approach, emphasizing empirical evidence and adaptability in the face of the unknown. Their expertise in decryption algorithms and signal analysis is pivotal to the team's mission, as they work on deciphering extraterrestrial signals and engaging in interstellar communication. This involves isolating signal harmonics, decrypting alien messages, and interpreting the alien signals for further analysis [Data: Entities (2, 148, 166, 180, 192); Claims (36, 39, 54, 61, 68, 79)].
|
||||
Dr. Hayes is known for their analytical and skeptical approach, emphasizing empirical evidence and adaptability in the face of the unknown. This mindset is particularly valuable when the team explores underground facilities, where potential data and evidence could be discovered. Dr. Hayes's skills in decryption algorithms and signal analysis are pivotal to the team's mission, as they work on deciphering extraterrestrial signals and engaging in interstellar communication [Data: Entities (2, 124, 180, 166); Claims (12, 13, 49, 54, 68)].
|
||||
|
||||
### Collaboration and Relationships
|
||||
|
||||
Dr. Hayes works closely with Alex Mercer, another key member of the Paranormal Military Squad. Their collaboration is marked by mutual respect and understanding, as they both contribute their analytical skills to the mission. Together, they focus on understanding alien code and responding to alien messages, which is a cornerstone of their operation at Dulce Base. Additionally, Dr. Hayes collaborates with other team members like Sam Rivera and Taylor Cruz, each bringing their unique expertise to the mission [Data: Relationships (1, 4, 9, 21, 34); Claims (18, 42)].
|
||||
Dr. Hayes collaborates closely with Alex Mercer, another key member of the Paranormal Military Squad. Their partnership is characterized by mutual respect and understanding, as they work together to interpret alien signals and respond to alien messages. This collaboration is crucial for the success of their mission at Dulce Base, highlighting the importance of their roles in this unique and challenging field [Data: Relationships (1, 4, 67); Claims (18, 42)].
|
||||
|
||||
### Challenges and Skepticism
|
||||
### Contributions and Achievements
|
||||
|
||||
Throughout their mission, Dr. Hayes maintains a critical and methodical approach, often reflecting on the potential data and evidence that could be found in their investigations. This skepticism is particularly evident when the team descends into an underground facility, where Dr. Hayes remains cautious about non-empirical possibilities. Their role is not only to analyze and interpret data but also to ensure that the team's efforts are grounded in scientific rigor [Data: Entities (2, 124); Claims (12, 13, 26)].
|
||||
Dr. Hayes has made significant contributions to the team's objectives, including analyzing signal disruptions related to star alignments and discovering warnings within alien messages. These achievements underscore their role as a central figure in the quest to understand and interact with alien entities, bringing a critical and methodical approach to the team's extraordinary endeavors [Data: Claims (36, 39, 84)].
|
||||
|
||||
In summary, Dr. Jordan Hayes is a central figure in the Paranormal Military Squad, bringing a critical and methodical approach to the team's extraordinary endeavors in understanding and interacting with alien entities. Their work at Dulce Base is characterized by a blend of scientific expertise, collaboration, and a cautious yet open-minded approach to the unknown.
|
||||
In summary, Dr. Jordan Hayes is a vital member of the Paranormal Military Squad, whose expertise in alien code deciphering and signal analysis is essential for the team's mission to communicate with extraterrestrial intelligence. Their analytical mindset and collaborative efforts with colleagues like Alex Mercer further enhance their contributions to the team's success at Dulce Base.
|
||||
</pre>
|
||||
</div>
|
||||
</div>
|
||||
@ -3982,7 +3978,7 @@ print(candidate_questions.response)</div>
|
||||
<div class="jp-OutputArea-child">
|
||||
<div class="jp-OutputPrompt jp-OutputArea-prompt"></div>
|
||||
<div class="jp-RenderedText jp-OutputArea-output" data-mime-type="text/plain" tabindex="0">
|
||||
<pre>['- What is the role of Alex Mercer at the Dulce Military Base?', '- How does the Paranormal Military Squad operate within the Dulce Military Base?', '- What are the main objectives of Operation: Dulce at the Dulce Military Base?', '- How does the Dulce Military Base facilitate communication with extraterrestrial intelligence?', '- What is the significance of the Dulce Military Base in the context of interstellar communication?']
|
||||
<pre>['- What is the primary mission of the Paranormal Military Squad at the Dulce Military Base?', '- How does Alex Mercer contribute to the operations at Dulce Base?', '- What role does the Dulce Military Base play in extraterrestrial communication?', '- Who are the key members of the team stationed at Dulce Base, and what are their responsibilities?', '- What are the challenges faced by the team at Dulce Base during Operation: Dulce?']
|
||||
</pre>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@ -1036,6 +1036,33 @@
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#configuration" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Configuration
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#how-to-use" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
How to Use
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#learn-more" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Learn More
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
@ -1442,6 +1469,33 @@
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#configuration" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Configuration
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#how-to-use" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
How to Use
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#learn-more" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Learn More
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
@ -1470,29 +1524,23 @@
|
||||
<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.
|
||||
|
||||
## Configuration
|
||||
|
||||
Below are the key parameters of the [DRIFTSearch class](https://github.com/microsoft/graphrag/blob/main//graphrag/query/structured_search/drift_search/search.py):
|
||||
|
||||
- `llm`: OpenAI model object to be used for response generation
|
||||
- `context_builder`: [context builder](https://github.com/microsoft/graphrag/blob/main/graphrag/query/structured_search/drift_search/drift_context.py) object to be used for preparing context data from community reports and query information
|
||||
- `config`: model to define the DRIFT Search hyperparameters. [DRIFT Config model](https://github.com/microsoft/graphrag/blob/main/graphrag/config/models/drift_config.py)
|
||||
- `token_encoder`: token encoder for tracking the budget for the algorithm.
|
||||
- `query_state`: a state object as defined in [Query State](https://github.com/microsoft/graphrag/blob/main/graphrag/query/structured_search/drift_search/state.py) that allows to track execution of a DRIFT Search instance, alongside follow ups and [DRIFT actions](https://github.com/microsoft/graphrag/blob/main/graphrag/query/structured_search/drift_search/action.py).
|
||||
|
||||
## How to Use
|
||||
|
||||
An example of a global search scenario can be found in the following [notebook](../examples_notebooks/drift_search.ipynb).
|
||||
|
||||
## Learn More
|
||||
|
||||
For a more in-depth look at the DRIFT search method, please refer to our [DRIFT Search blog post](https://www.microsoft.com/en-us/research/blog/introducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiency/)
|
||||
<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.</p>
|
||||
<h2 id="configuration">Configuration</h2>
|
||||
<p>Below are the key parameters of the <a href="https://github.com/microsoft/graphrag/blob/main//graphrag/query/structured_search/drift_search/search.py">DRIFTSearch class</a>:</p>
|
||||
<ul>
|
||||
<li><code>llm</code>: OpenAI model object to be used for response generation</li>
|
||||
<li><code>context_builder</code>: <a href="https://github.com/microsoft/graphrag/blob/main/graphrag/query/structured_search/drift_search/drift_context.py">context builder</a> object to be used for preparing context data from community reports and query information</li>
|
||||
<li><code>config</code>: model to define the DRIFT Search hyperparameters. <a href="https://github.com/microsoft/graphrag/blob/main/graphrag/config/models/drift_config.py">DRIFT Config model</a></li>
|
||||
<li><code>token_encoder</code>: token encoder for tracking the budget for the algorithm.</li>
|
||||
<li><code>query_state</code>: a state object as defined in <a href="https://github.com/microsoft/graphrag/blob/main/graphrag/query/structured_search/drift_search/state.py">Query State</a> that allows to track execution of a DRIFT Search instance, alongside follow ups and <a href="https://github.com/microsoft/graphrag/blob/main/graphrag/query/structured_search/drift_search/action.py">DRIFT actions</a>.</li>
|
||||
</ul>
|
||||
<h2 id="how-to-use">How to Use</h2>
|
||||
<p>An example of a global search scenario can be found in the following <a href="../../examples_notebooks/drift_search/">notebook</a>.</p>
|
||||
<h2 id="learn-more">Learn More</h2>
|
||||
<p>For a more in-depth look at the DRIFT search method, please refer to our <a href="https://www.microsoft.com/en-us/research/blog/introducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiency/">DRIFT Search blog post</a></p>
|
||||
|
||||
|
||||
|
||||
|
||||
File diff suppressed because one or more lines are too long
Loading…
x
Reference in New Issue
Block a user