rixty/SillyTavern
1
0
Fork 0
mirror of https://github.com/SillyTavern/SillyTavern.git synced 2025-06-05 21:59:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add ollama and llamacpp as vector sources

Browse Source
This commit is contained in:
Cohee
2024-05-28 22:54:50 +03:00
parent c858fccc5f
commit 2b3dfc5ae2
6 changed files with 286 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
public/scripts/extensions/vectors/settings.html
View File

@ -12,14 +12,37 @@
<select id="vectors_source" class="text_pole">
<option value="cohere">Cohere</option>
<option value="extras">Extras</option>
<option value="palm">Google MakerSuite (PaLM)</option>
<option value="palm">Google MakerSuite</option>
<option value="llamacpp">llama.cpp</option>
<option value="transformers">Local (Transformers)</option>
<option value="ollama">Ollama</option>
<option value="openai">OpenAI</option>
<option value="mistral">MistralAI</option>
<option value="nomicai">NomicAI</option>
<option value="openai">OpenAI</option>
<option value="togetherai">TogetherAI</option>
</select>
</div>
<div class="flex-container flexFlowColumn" id="ollama_vectorsModel">
<label for="vectors_ollama_model">
Vectorization Model
</label>
<input id="vectors_ollama_model" class="text_pole" type="text" placeholder="Model tag, e.g. llama3" />
<label for="vectors_ollama_keep" class="checkbox_label" title="When checked, the model will not be unloaded after use.">
<input id="vectors_ollama_keep" type="checkbox" />
<span>Keep model in memory</span>
</label>
<i>
Hint: Download models and set the URL in the API connection settings.
</i>
</div>
<div class="flex-container flexFlowColumn" id="llamacpp_vectorsModel">
<span>
The server MUST be started with the <code>--embedding</code> flag to use this feature!
</span>
<i>
Hint: Set the URL in the API connection settings.
</i>
</div>
<div class="flex-container flexFlowColumn" id="openai_vectorsModel">
<label for="vectors_openai_model">
Vectorization Model