Skip to content

Commit

Permalink
deploy: 86f0843
Browse files Browse the repository at this point in the history
  • Loading branch information
github-actions[bot] committed Jul 2, 2024
1 parent bd04b18 commit 47a3a3a
Show file tree
Hide file tree
Showing 5 changed files with 35 additions and 2 deletions.
Binary file modified .doctrees/developer_notes/index.doctree
Binary file not shown.
Binary file modified .doctrees/environment.pickle
Binary file not shown.
3 changes: 2 additions & 1 deletion _sources/developer_notes/index.rst.txt
Original file line number Diff line number Diff line change
Expand Up @@ -76,6 +76,7 @@ Code path: :ref:`lightrag.core <apis-core>`.

RAG Essentials
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

RAG components
^^^^^^^^^^^^^^^^^^^

Expand All @@ -98,14 +99,14 @@ Code path: :ref:`lightrag.core<apis-core>`. For abstract classes:
- ``ModelClient`` is the protocol and base class for LightRAG to **integrate all models**, either APIs or local, LLMs or Embedding models or any others.
* - :doc:`generator`
- The orchestrator for LLM prediction. It streamlines three components: `ModelClient`, `Prompt`, and `output_processors` and works with optimizer for prompt optimization.
- The **center component** that orchestrates the model client(LLMs in particular), prompt, and output processors for format parsing or any post processing.
* - :doc:`output_parsers`
- The component that parses the output string to structured data.
* - :doc:`embedder`
- The component that orchestrates model client (Embedding models in particular) and output processors.
* - :doc:`retriever`
- The base class for all retrievers who in particular retrieve relevant documents from a given database to add **context** to the generator.


Data Pipeline and Storage
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Expand Down
32 changes: 32 additions & 0 deletions developer_notes/index.html
Original file line number Diff line number Diff line change
Expand Up @@ -511,6 +511,38 @@ <h4>RAG components<a class="headerlink" href="#rag-components" title="Link to th
<li><p><code class="docutils literal notranslate"><span class="pre">ModelClient</span></code>: the functional subclass is in <a class="reference internal" href="../apis/components/components.model_client.html#components-model-client"><span class="std std-ref">lightrag.components.model_client</span></a>.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">Retriever</span></code>: the functional subclass is in <a class="reference internal" href="../apis/components/components.retriever.html#components-retriever"><span class="std std-ref">lightrag.components.retriever</span></a>.</p></li>
</ul>
<div class="pst-scrollable-table-container"><table class="table">
<colgroup>
<col style="width: 20.0%" />
<col style="width: 80.0%" />
</colgroup>
<thead>
<tr class="row-odd"><th class="head"><p>Part</p></th>
<th class="head"><p>Description</p></th>
</tr>
</thead>
<tbody>
<tr class="row-even"><td><p><a class="reference internal" href="prompt.html"><span class="doc">Prompt</span></a></p></td>
<td><p>Built on <cite>jinja2</cite>, it programmatically and flexibly formats prompts as input to the generator.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="model_client.html"><span class="doc">ModelClient</span></a></p></td>
<td><p><code class="docutils literal notranslate"><span class="pre">ModelClient</span></code> is the protocol and base class for LightRAG to <strong>integrate all models</strong>, either APIs or local, LLMs or Embedding models or any others.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="generator.html"><span class="doc">Generator</span></a></p></td>
<td><p>The orchestrator for LLM prediction. It streamlines three components: <cite>ModelClient</cite>, <cite>Prompt</cite>, and <cite>output_processors</cite> and works with optimizer for prompt optimization.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="output_parsers.html"><span class="doc">Parser</span></a></p></td>
<td><p>The component that parses the output string to structured data.</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="embedder.html"><span class="doc">Embedder</span></a></p></td>
<td><p>The component that orchestrates model client (Embedding models in particular) and output processors.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="retriever.html"><span class="doc">Retriever</span></a></p></td>
<td><p>The base class for all retrievers who in particular retrieve relevant documents from a given database to add <strong>context</strong> to the generator.</p></td>
</tr>
</tbody>
</table>
</div>
</section>
<section id="data-pipeline-and-storage">
<h4>Data Pipeline and Storage<a class="headerlink" href="#data-pipeline-and-storage" title="Link to this heading">#</a></h4>
Expand Down
2 changes: 1 addition & 1 deletion searchindex.js

Large diffs are not rendered by default.

0 comments on commit 47a3a3a

Please sign in to comment.