Deploying to gh-pages from @ microsoft/graphrag@4b57760fea 🚀

This commit is contained in:
darthtrevino 2024-04-05 22:54:01 +00:00
parent d52d98058b
commit 64ce17f03f

View File

@ -312,28 +312,21 @@ It shows how to use the system to index some text, and then use the indexed data
</div>
<p>Next we'll inject some required config variables:</p>
<h2>Set Up Environment Variables</h2>
<p>First let's make sure to setup the required environment variables:</p>
<ul>
<li><code>GRAPHRAG_API_KEY</code> - API Key for executing the model, will fallback to <code>OPENAI_API_KEY</code> if one is not provided.</li>
<li><code>GRAPHRAG_LLM_MODEL</code> - Model to use for Chat Completions.</li>
<li><code>GRAPHRAG_LLM_MODEL_SUPPORTS_JSON</code> - This will signal to the indexing engine that you're using a model capable of JSON-mode output (e.g. gpt-4 or gpt-3.5-turbo). We <em>highly recommend</em> enabling this to avoid malformed JSON errors during indexing.</li>
<li><code>GRAPHRAG_EMBEDDING_MODEL</code> - Model to use for Embeddings.</li>
<li><code>GRAPHRAG_INPUT_TYPE</code> - Type of input data, can be <code>text</code> or <code>csv</code>.</li>
<li><code>GRAPHRAG_API_BASE</code> - Base URL for the Azure OpenAI. Only required for Azure OpenAI users.</li>
<li><code>GRAPHRAG_LLM_DEPLOYMENT_NAME</code> - Deployment name for the Chat Completions model. Only required for Azure OpenAI users.</li>
<li><code>GRAPHRAG_EMBEDDING_DEPLOYMENT_NAME</code> - Deployment name for the Embeddings model. Only required for Azure OpenAI users.</li>
</ul>
<p>First let's make sure to setup the required environment variables. For details on these environment variables, and what environment variables are available, see the <a href="/graphrag/posts/config/env_vars/">environment variables documentation</a>.</p>
<h4><ins>OpenAI and Azure OpenAI</ins></h4>
<p>To get started, let's set the base environment variables.</p>
<div style="position: relative">
<pre class="language-sh"><code id="code-99" class="language-sh"><span class="token builtin class-name">export</span> <span class="token assign-left variable">GRAPHRAG_API_KEY</span><span class="token operator">=</span><span class="token string">"&lt;api_key>"</span> <span class="token operator">&amp;&amp;</span> <span class="token punctuation">\</span>
<pre class="language-sh"><code id="code-54" class="language-sh">
To get started, let's <span class="token builtin class-name">set</span> the base environment variables.
```sh
<span class="token builtin class-name">export</span> <span class="token assign-left variable">GRAPHRAG_API_KEY</span><span class="token operator">=</span><span class="token string">"&lt;api_key>"</span> <span class="token operator">&amp;&amp;</span> <span class="token punctuation">\</span>
<span class="token builtin class-name">export</span> <span class="token assign-left variable">GRAPHRAG_LLM_MODEL</span><span class="token operator">=</span><span class="token string">"&lt;chat_completions_model>"</span> <span class="token operator">&amp;&amp;</span> <span class="token punctuation">\</span>
<span class="token builtin class-name">export</span> <span class="token assign-left variable">GRAPHRAG_LLM_MODEL_SUPPORTS_JSON</span><span class="token operator">=</span><span class="token string">"True"</span> <span class="token operator">&amp;&amp;</span> <span class="token punctuation">\</span>
<span class="token builtin class-name">export</span> <span class="token assign-left variable">GRAPHRAG_EMBEDDING_MODEL</span><span class="token operator">=</span><span class="token string">"&lt;embeddings_model>"</span> <span class="token operator">&amp;&amp;</span> <span class="token punctuation">\</span>
<span class="token builtin class-name">export</span> <span class="token assign-left variable">GRAPHRAG_INPUT_TYPE</span><span class="token operator">=</span><span class="token string">"text"</span></code></pre>
<button class="code-copy " data-clipboard-target="#code-99" style="position: absolute; top: 7.5px; right: 6px; padding-top: 3px; cursor: pointer; outline: none; opacity: 0.8;" title="Copy">
<button class="code-copy " data-clipboard-target="#code-54" style="position: absolute; top: 7.5px; right: 6px; padding-top: 3px; cursor: pointer; outline: none; opacity: 0.8;" title="Copy">
<span style="display:inline-block;background:url(https://api.iconify.design/mdi/content-copy.svg) no-repeat center center / contain;width: 16px; height: 16px;" class=""></span>
</button>
</div>
@ -341,14 +334,14 @@ It shows how to use the system to index some text, and then use the indexed data
<p>In addition, Azure OpenAI users should set the following env-vars.</p>
<div style="position: relative">
<pre class="language-sh"><code id="code-106" class="language-sh"><span class="token builtin class-name">export</span> <span class="token assign-left variable">GRAPHRAG_API_BASE</span><span class="token operator">=</span><span class="token string">"https://&lt;domain>.openai.azure.com"</span> <span class="token operator">&amp;&amp;</span> <span class="token punctuation">\</span>
<pre class="language-sh"><code id="code-61" class="language-sh"><span class="token builtin class-name">export</span> <span class="token assign-left variable">GRAPHRAG_API_BASE</span><span class="token operator">=</span><span class="token string">"https://&lt;domain>.openai.azure.com"</span> <span class="token operator">&amp;&amp;</span> <span class="token punctuation">\</span>
<span class="token builtin class-name">export</span> <span class="token assign-left variable">GRAPHRAG_API_VERSION</span><span class="token operator">=</span><span class="token string">"2024-02-15-preview"</span> <span class="token operator">&amp;&amp;</span> <span class="token punctuation">\</span>
<span class="token builtin class-name">export</span> GRAPHRAG_LLM_API_TYPE <span class="token operator">=</span> <span class="token string">"azure_openai_chat"</span> <span class="token operator">&amp;&amp;</span> <span class="token punctuation">\</span>
<span class="token builtin class-name">export</span> <span class="token assign-left variable">GRAPHRAG_LLM_DEPLOYMENT_NAME</span><span class="token operator">=</span><span class="token string">"&lt;chat_completions_deployment_name>"</span> <span class="token operator">&amp;&amp;</span> <span class="token punctuation">\</span>
<span class="token builtin class-name">export</span> GRAPHRAG_EMBEDDING_API_TYPE <span class="token operator">=</span> <span class="token string">"azure_openai_embedding"</span> <span class="token operator">&amp;&amp;</span> <span class="token punctuation">\</span>
<span class="token builtin class-name">export</span> <span class="token assign-left variable">GRAPHRAG_EMBEDDING_DEPLOYMENT_NAME</span><span class="token operator">=</span><span class="token string">"&lt;embeddings_deployment_name>"</span></code></pre>
<button class="code-copy " data-clipboard-target="#code-106" style="position: absolute; top: 7.5px; right: 6px; padding-top: 3px; cursor: pointer; outline: none; opacity: 0.8;" title="Copy">
<button class="code-copy " data-clipboard-target="#code-61" style="position: absolute; top: 7.5px; right: 6px; padding-top: 3px; cursor: pointer; outline: none; opacity: 0.8;" title="Copy">
<span style="display:inline-block;background:url(https://api.iconify.design/mdi/content-copy.svg) no-repeat center center / contain;width: 16px; height: 16px;" class=""></span>
</button>
</div>
@ -358,9 +351,9 @@ For more details about using the CLI, refer to the <a href="/graphrag/posts/quer
<p>Finally we'll run the pipeline!</p>
<div style="position: relative">
<pre class="language-sh"><code id="code-116" class="language-sh">python <span class="token parameter variable">-m</span> graphrag.index <span class="token parameter variable">--root</span> ./ragtest</code></pre>
<pre class="language-sh"><code id="code-71" class="language-sh">python <span class="token parameter variable">-m</span> graphrag.index <span class="token parameter variable">--root</span> ./ragtest</code></pre>
<button class="code-copy " data-clipboard-target="#code-116" style="position: absolute; top: 7.5px; right: 6px; padding-top: 3px; cursor: pointer; outline: none; opacity: 0.8;" title="Copy">
<button class="code-copy " data-clipboard-target="#code-71" style="position: absolute; top: 7.5px; right: 6px; padding-top: 3px; cursor: pointer; outline: none; opacity: 0.8;" title="Copy">
<span style="display:inline-block;background:url(https://api.iconify.design/mdi/content-copy.svg) no-repeat center center / contain;width: 16px; height: 16px;" class=""></span>
</button>
</div>
@ -373,24 +366,24 @@ Once the pipeline is complete, you should see a new folder called <code>./ragtes
<p>Here is an example using Global search to ask a high-level question:</p>
<div style="position: relative">
<pre class="language-sh"><code id="code-135" class="language-sh">python <span class="token parameter variable">-m</span> graphrag.query <span class="token punctuation">\</span>
<pre class="language-sh"><code id="code-90" class="language-sh">python <span class="token parameter variable">-m</span> graphrag.query <span class="token punctuation">\</span>
<span class="token parameter variable">--data</span> ./ragtest/output/<span class="token operator">&lt;</span>timestamp<span class="token operator">></span>/artifacts <span class="token punctuation">\</span>
<span class="token parameter variable">--method</span> global <span class="token punctuation">\</span>
<span class="token string">"What are the top themes in this story?"</span></code></pre>
<button class="code-copy " data-clipboard-target="#code-135" style="position: absolute; top: 7.5px; right: 6px; padding-top: 3px; cursor: pointer; outline: none; opacity: 0.8;" title="Copy">
<button class="code-copy " data-clipboard-target="#code-90" style="position: absolute; top: 7.5px; right: 6px; padding-top: 3px; cursor: pointer; outline: none; opacity: 0.8;" title="Copy">
<span style="display:inline-block;background:url(https://api.iconify.design/mdi/content-copy.svg) no-repeat center center / contain;width: 16px; height: 16px;" class=""></span>
</button>
</div>
<p>Here is an example using Local search to ask a more specific question about a particular character:</p>
<div style="position: relative">
<pre class="language-sh"><code id="code-139" class="language-sh">python <span class="token parameter variable">-m</span> graphrag.query <span class="token punctuation">\</span>
<pre class="language-sh"><code id="code-94" class="language-sh">python <span class="token parameter variable">-m</span> graphrag.query <span class="token punctuation">\</span>
<span class="token parameter variable">--data</span> ./ragtest/output/<span class="token operator">&lt;</span>timestamp<span class="token operator">></span>/artifacts <span class="token punctuation">\</span>
<span class="token parameter variable">--method</span> <span class="token builtin class-name">local</span> <span class="token punctuation">\</span>
<span class="token string">"Who is Scrooge, and what are his main relationships?"</span></code></pre>
<button class="code-copy " data-clipboard-target="#code-139" style="position: absolute; top: 7.5px; right: 6px; padding-top: 3px; cursor: pointer; outline: none; opacity: 0.8;" title="Copy">
<button class="code-copy " data-clipboard-target="#code-94" style="position: absolute; top: 7.5px; right: 6px; padding-top: 3px; cursor: pointer; outline: none; opacity: 0.8;" title="Copy">
<span style="display:inline-block;background:url(https://api.iconify.design/mdi/content-copy.svg) no-repeat center center / contain;width: 16px; height: 16px;" class=""></span>
</button>
</div>