kanshan/graphrag
1
0
Fork 0
mirror of https://github.com/microsoft/graphrag.git synced 2026-01-22 20:01:49 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

Deploying to gh-pages from @ microsoft/graphrag@9d99f323ea 🚀

Browse Source
This commit is contained in:
darthtrevino 2024-07-26 22:09:04 +00:00
parent 24a13a2c08
commit edf2f89ab6
3 changed files with 17 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
data/operation_dulce/dataset.zip
View File

Binary file not shown.

16
posts/config/env_vars/index.html
View File

@ -873,7 +873,7 @@ a {
<td>The encoding model to use for chunking.</td>
<td><code>str</code></td>
<td>optional</td>
<td><code>None</code></td>
<td>The top-level encoding model.</td>
</tr>
</tbody>
</table>
@ -911,6 +911,13 @@ a {
<td><code>organization,person,event,geo</code></td>
</tr>
<tr>
<td><code>GRAPHRAG_ENTITY_EXTRACTION_ENCODING_MODEL</code></td>
<td>The encoding model to use for entity extraction.</td>
<td><code>str</code></td>
<td>optional</td>
<td>The top-level encoding model.</td>
</tr>
<tr>
<td><code>GRAPHRAG_SUMMARIZE_DESCRIPTIONS_PROMPT_FILE</code></td>
<td>The path (relative to the root) of an description summarization prompt template text file.</td>
<td><code>str</code></td>
@ -953,6 +960,13 @@ a {
<td>1</td>
</tr>
<tr>
<td><code>GRAPHRAG_CLAIM_EXTRACTION_ENCODING_MODEL</code></td>
<td>The encoding model to use for claim extraction.</td>
<td><code>str</code></td>
<td>optional</td>
<td>The top-level encoding model</td>
</tr>
<tr>
<td><code>GRAPHRAG_COMMUNITY_REPORTS_PROMPT_FILE</code></td>
<td>The community reports extraction prompt to utilize.</td>
<td><code>string</code></td>

2
posts/config/json_yaml/index.html
View File

@ -411,6 +411,7 @@ API_KEY=some_api_key
<li><code>prompt</code> <strong>str</strong> - The prompt file to use.</li>
<li><code>entity_types</code> <strong>list[str]</strong> - The entity types to identify.</li>
<li><code>max_gleanings</code> <strong>int</strong> - The maximum number of gleaning cycles to use.</li>
<li><code>encoding_model</code> <strong>str</strong> - The text encoding model to use. By default, this will use the top-level encoding model.</li>
<li><code>strategy</code> <strong>dict</strong> - Fully override the entity extraction strategy.</li>
</ul>
<h2>summarize_descriptions</h2>
@ -433,6 +434,7 @@ API_KEY=some_api_key
<li><code>prompt</code> <strong>str</strong> - The prompt file to use.</li>
<li><code>description</code> <strong>str</strong> - Describes the types of claims we want to extract.</li>
<li><code>max_gleanings</code> <strong>int</strong> - The maximum number of gleaning cycles to use.</li>
<li><code>encoding_model</code> <strong>str</strong> - The text encoding model to use. By default, this will use the top-level encoding model.</li>
<li><code>strategy</code> <strong>dict</strong> - Fully override the claim extraction strategy.</li>
</ul>
<h2>community_reports</h2>