Deployed ed0741c with MkDocs version: 1.5.3

card_format/index.html

@@ -109,8 +109,8 @@
             <div class="section" itemprop="articleBody">
 
                 <h3 id="card-format">Card Format</h3>
-<p>See <a href="https://zoltanai.github.io/character-editor/">character editor</a>.<BR>
-There are few example cards included like'Skynet', <a href="https://chub.ai/characters/potato7295/harry-potter-bffe8945">'Harry Potter'</a> and <a href="https://chub.ai/characters/Mafiuz/bronya-zaychik-silverwing-n-ex-926eb8d4">'Bronya Zaychik'</a><BR>
+<p>See <a href="https://character-tools.srjuggernaut.dev/character-editor">character editor</a>.<BR>
+There are few example cards included like'Skynet' and 'Shodan'<BR>
 'name' : 'char_name'<br>
 The name for the ai character. When using json or yaml, this is expected to correspond to avatar image. name.png or name.jpg.<br>
 'description' : 'char_persona'<br>

configs/index.html

@@ -149,10 +149,6 @@ <h3 id="basic-configs">Basic Configs</h3>
 <td>Prompt template are stored here</td>
 </tr>
 <tr>
-<td>PROMPT_TEMPLATE</td>
-<td>question_generation_template.json</td>
-</tr>
-<tr>
 <td>REPLACE_YOU</td>
 <td>Replace references to "You" in card with "User"</td>
 </tr>
@@ -161,19 +157,15 @@ <h3 id="basic-configs">Basic Configs</h3>
 <td>dir for NER keys for chroma</td>
 </tr>
 <tr>
-<td>USE_KEY_STORAGE</td>
-<td>Use NER keys for Chroma metadata</td>
-</tr>
-<tr>
-<td>COLLECTION</td>
-<td>Chroma collection to use. "" to disable Chroma</td>
+<td>COLLECTION_CONFIG</td>
+<td>Path to run config file for collection and prompt</td>
 </tr>
 <tr>
 <td>EMBEDDINGS_TYPE</td>
 <td>llama/spacy/hugginface</td>
 </tr>
 <tr>
-<td>EMBEDDINGS_model</td>
+<td>EMBEDDINGS_MODEL</td>
 <td>spacy/hugginface model name (needs to be installed)</td>
 </tr>
 <tr>
@@ -214,7 +206,7 @@ <h3 id="basic-configs">Basic Configs</h3>
 </tr>
 <tr>
 <td>USE_MMAP</td>
-<td>Allows only the necessary parts to be loaded into memory and offloading the rest. Default true</td>
+<td>Allows only the necessary parts to be loaded into memory and offloading the rest. Default false</td>
 </tr>
 <tr>
 <td>TEMPERATURE</td>
@@ -249,6 +241,10 @@ <h3 id="basic-configs">Basic Configs</h3>
 <td>Context size</td>
 </tr>
 <tr>
+<td>N_BATCH</td>
+<td>Message write batch size</td>
+</tr>
+<tr>
 <td>MAX_TOKENS</td>
 <td>Max tokens. Default 256</td>
 </tr>
@@ -259,6 +255,9 @@ <h3 id="general-configs">General Configs</h3>
 <p>Filters folder defines the general webscrape filters to clean the documents. This file uses regex and can easily be modified to add extra filtering.</p>
 <p>Parse_configs defines the expected csv column structure and ner type parsing. This includes noun engrams, entities, noun chunks and parse type.</p>
 <p>Web scrape configs define the web pages fo a scrape. This is convinient if you want to scrape multiple pages.</p>
+<h3 id="run-config">Run Config</h3>
+<p>The run config in run_config.json in the run_files folder defines the options for chat run settings. The run config sets the defaults for message collection, context collection and for the prompt template. The config also gives the list of alternative collection and prompt settings. These can be changed while the chat is running from the chat settings menu.
+<img alt="Settings Panel" src="../img/settings_panel.png" /></p>
 
             </div>
           </div><footer>

creating_embeddings/index.html

@@ -118,7 +118,7 @@ <h3 id="creating-embeddings">Creating embeddings</h3>
 python -m spacy download en_core_web_lg
 </code></pre>
 <p>You might want to play with the chunk size and overlap based on your text documents<BR>
-The example documents include a txt file for skynet embeddings and json lorebooks for <a href="https://chub.ai/lorebooks/deadgirlz/hogwarts-legacy-lore-b819ccba">Hogwarts</a> and <a href="https://chub.ai/lorebooks/Zareh-Haadris/lorebook-honkai-impact-b1fcfc23">Honkai Impact</a><BR>
+The example documents include a txt file for 'Skynet' and 'Shodan'<BR>
 The supported lorebook formats are chub inferred AgnAIstic and SillyTavern original source.
 For pdf files there is a pdf file of short stories from Fyodor Dostoyevsky included The source is Internet Archive, the copy is in public domain. The pdf text quality is quite poor thought, so I recommend getting another file.</p>
 <p>Performance for files over 200mb is not great. Parsing a large text with a large keyfile will result in poor performance. It's more effective to have smaller colletions that have their own keyfiles rather that one large collection with one keyfile. I recommend splitting sollections my subject category and then switching as needed.</p>

getting_started/index.html

@@ -125,7 +125,7 @@
 <p>Note that this example is for powershell and for the latest llama-cpp-python. You will need to change the command based on the terminal and the llama-cpp-python version.</BR></p>
 <p>Get a gguf model from a site like
 <a href="https://huggingface.co/models?sort=modified&amp;search=theBloke+gguf">The Bloke</a>
-and a character card and lorebooks from a site like <a href="https://chub.ai/">Chub.ai</a> or make your own with <a href="https://zoltanai.github.io/character-editor/">character editor</a><BR></p>
+and a character card and lorebooks from a site like <a href="https://www.characterhub.org/">Character hub</a> or make your own with <a href="https://character-tools.srjuggernaut.dev/character-editor">character editor</a><BR></p>
 <p>Change the .env_test to .env and make sure that the correct folders exist.</BR></p>
 <p>You can set the collection to "" and try the chatbot by running:</p>
 <pre><code>chainlit run character_chat.py

index.html

@@ -163,5 +163,5 @@ <h1 id="llama-cpp-chat-memory">llama-cpp-chat-memory</h1>
 
 <!--
 MkDocs version : 1.5.3
-Build Date UTC : 2024-05-19 12:20:02.653379+00:00
+Build Date UTC : 2024-06-08 11:03:26.487232+00:00
 -->

prompt_support/index.html

@@ -110,7 +110,7 @@
 
                 <h3 id="prompt-support">Prompt Support</h3>
 <p>Supports alpaca and mistral text prompts, V2 and tavern style json and yaml files and V2 and tavern png cards. Avatar images need to be in the same folder as the prompt file. V2 and Tavern png files get a copy of the image without exif data in the project temp file. Inbuilt lorebooks are currently not supported</p>
-<p>See <a href="https://chub.ai/">Chub.ai</a> for some character cards or make your own with <a href="https://zoltanai.github.io/character-editor/">character editor</a>.<BR></p>
+<p>See <a href="https://www.characterhub.org/">Character hub</a> for some character cards or make your own with <a href="https://character-tools.srjuggernaut.dev/character-editor">character editor</a>.<BR></p>
 
             </div>
           </div><footer>

sitemap.xml

@@ -2,72 +2,72 @@
 <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/UNLICENSE/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/card_format/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/configs/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/creating_embeddings/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/csv/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/examples/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/getting_started/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/named_entity_recognition/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/preparing_the_env/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/prompt_support/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/running_the_chatbot/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/running_the_env/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
     <url>
          <loc>https://ossirytk.github.io/llama-cpp-chat-memory/webscraping/</loc>
-         <lastmod>2024-05-19</lastmod>
+         <lastmod>2024-06-08</lastmod>
          <changefreq>daily</changefreq>
     </url>
 </urlset>