yujunjun/graphrag
1
0
Fork 0
mirror of https://github.com/microsoft/graphrag.git synced 2026-01-06 12:11:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Deploying to gh-pages from @ microsoft/graphrag@7e00955082 🚀

Browse Source
This commit is contained in:
AlonsoGuevara 2024-06-19 21:52:20 +00:00
parent dedffbada7
commit c0ae5d3e8a
3 changed files with 13 additions and 13 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.

18
posts/config/env_vars/index.html
View File

@ -288,7 +288,7 @@ a {
<h1>Default Configuration Mode (using Env Vars)</h1>
<h2>Text-Embeddings Customization</h2>
<p>By default, the GraphRAG indexer will only emit embeddings required for our query methods. However, the model has embeddings defined for all plaintext fields, and these can be generated by setting the <code>GRAPHRAG_EMBEDDING_TARGET</code> environment variable to <code>all</code>.</p>
<p>If the embedding target is <code>all</code>, and you want to only embed a subset of these fields, you may specify which embeddings to skip using the <code>GRAPHRAG_EMBEDDING_SKIP</code> argument described below.</p>
<p>If the embedding target is <code>all</code>, and you want to only embed a subset of these fields, you may specify which embeddings to skip using the <code>GRAPHRAG_EMBEDDING_SKIP</code> argument described below.</p>
<h3>Embedded Fields</h3>
<ul>
<li><code>text_unit.text</code></li>
@ -628,7 +628,7 @@ a {
<tr>
<td><code>GRAPHRAG_EMBEDDING_RPM</code></td>
<td></td>
<td>The number of requests per minute to allow for the embedding client. 0 = Bypass</td>
<td>The number of requests per minute to allow for the embedding client. 0 = Bypass</td>
<td><code>int</code></td>
<td>0</td>
</tr>
@ -699,7 +699,7 @@ a {
<tbody>
<tr>
<td><code>GRAPHRAG_INPUT_TYPE</code></td>
<td>The input storage type to use when reading files. (<code>file</code> or <code>blob</code>)</td>
<td>The input storage type to use when reading files. (<code>file</code> or <code>blob</code>)</td>
<td><code>str</code></td>
<td>optional</td>
<td><code>file</code></td>
@ -709,7 +709,7 @@ a {
<td>The file pattern regexp to use when reading input files from the input directory.</td>
<td><code>str</code></td>
<td>optional</td>
<td><code>.*\.csv$</code></td>
<td><code>.*\.txt$</code></td>
</tr>
<tr>
<td><code>GRAPHRAG_INPUT_SOURCE_COLUMN</code></td>
@ -755,7 +755,7 @@ a {
</tr>
<tr>
<td><code>GRAPHRAG_INPUT_STORAGE_ACCOUNT_BLOB_URL</code></td>
<td>The Azure Storage blob endpoint to use when in <code>blob</code> mode and using managed identity. Will have the format <code>https://&lt;storage_account_name&gt;.blob.core.windows.net</code></td>
<td>The Azure Storage blob endpoint to use when in <code>blob</code> mode and using managed identity. Will have the format <code>https://&lt;storage_account_name&gt;.blob.core.windows.net</code></td>
<td><code>str</code></td>
<td>optional</td>
<td><code>None</code></td>
@ -800,7 +800,7 @@ a {
<td>The type of input data, <code>csv</code> or <code>text</code></td>
<td><code>str</code></td>
<td>optional</td>
<td><code>csv</code></td>
<td><code>text</code></td>
</tr>
<tr>
<td><code>GRAPHRAG_INPUT_ENCODING</code></td>
@ -959,7 +959,7 @@ a {
</tr>
<tr>
<td><code>GRAPHRAG_STORAGE_STORAGE_ACCOUNT_BLOB_URL</code></td>
<td>The Azure Storage blob endpoint to use when in <code>blob</code> mode and using managed identity. Will have the format <code>https://&lt;storage_account_name&gt;.blob.core.windows.net</code></td>
<td>The Azure Storage blob endpoint to use when in <code>blob</code> mode and using managed identity. Will have the format <code>https://&lt;storage_account_name&gt;.blob.core.windows.net</code></td>
<td><code>str</code></td>
<td>optional</td>
<td>None</td>
@ -1009,7 +1009,7 @@ a {
</tr>
<tr>
<td><code>GRAPHRAG_CACHE_STORAGE_ACCOUNT_BLOB_URL</code></td>
<td>The Azure Storage blob endpoint to use when in <code>blob</code> mode and using managed identity. Will have the format <code>https://&lt;storage_account_name&gt;.blob.core.windows.net</code></td>
<td>The Azure Storage blob endpoint to use when in <code>blob</code> mode and using managed identity. Will have the format <code>https://&lt;storage_account_name&gt;.blob.core.windows.net</code></td>
<td><code>str</code></td>
<td>optional</td>
<td>None</td>
@ -1059,7 +1059,7 @@ a {
</tr>
<tr>
<td><code>GRAPHRAG_REPORTING_STORAGE_ACCOUNT_BLOB_URL</code></td>
<td>The Azure Storage blob endpoint to use when in <code>blob</code> mode and using managed identity. Will have the format <code>https://&lt;storage_account_name&gt;.blob.core.windows.net</code></td>
<td>The Azure Storage blob endpoint to use when in <code>blob</code> mode and using managed identity. Will have the format <code>https://&lt;storage_account_name&gt;.blob.core.windows.net</code></td>
<td><code>str</code></td>
<td>optional</td>
<td>None</td>

8
posts/config/template/index.html
View File

@ -323,14 +323,14 @@ the <code>--root</code> parameter on your Indexing Pipeline execution.</p>
<span class="token comment"># Required LLM Config</span>
<span class="token comment"># Input Data Configuration</span>
<span class="token assign-left variable">GRAPHRAG_INPUT_TYPE</span><span class="token operator">=</span>text
<span class="token assign-left variable">GRAPHRAG_INPUT_TYPE</span><span class="token operator">=</span><span class="token string">"file"</span>
<span class="token comment"># Plaintext Input Data Configuration</span>
<span class="token comment"># GRAPHRAG_INPUT_FILE_PATTERN=.*\.txt</span>
<span class="token comment"># CSV Input Data Configuration</span>
<span class="token assign-left variable">GRAPHRAG_INPUT_FILE_TYPE</span><span class="token operator">=</span><span class="token string">"csv"</span>
<span class="token assign-left variable">GRAPHRAG_INPUT_FILE_PATTERN</span><span class="token operator">=</span><span class="token string">".*\.csv$"</span>
<span class="token comment"># Text Input Data Configuration</span>
<span class="token assign-left variable">GRAPHRAG_INPUT_FILE_TYPE</span><span class="token operator">=</span><span class="token string">"text"</span>
<span class="token assign-left variable">GRAPHRAG_INPUT_FILE_PATTERN</span><span class="token operator">=</span><span class="token string">".*\.txt$"</span>
<span class="token assign-left variable">GRAPHRAG_INPUT_SOURCE_COLUMN</span><span class="token operator">=</span>source
<span class="token comment"># GRAPHRAG_INPUT_TIMESTAMP_COLUMN=None</span>
<span class="token comment"># GRAPHRAG_INPUT_TIMESTAMP_FORMAT=None</span>