adjust some things

README.md

@@ -10,7 +10,7 @@ The purpose of this server is to abstract your LLM backend from your frontend AP
 2. `python3 -m venv venv`
 3. `source venv/bin/activate`
 4. `pip install -r requirements.txt`
-5. `wget https://git.evulid.cc/attachments/89c87201-58b1-4e28-b8fd-d0b323c810c4 -O vllm_gptq-0.1.3-py3-none-any.whl && pip install vllm_gptq-0.1.3-py3-none-any.whl`
+5. `wget https://git.evulid.cc/attachments/89c87201-58b1-4e28-b8fd-d0b323c810c4 -O /tmp/vllm_gptq-0.1.3-py3-none-any.whl && pip install /tmp/vllm_gptq-0.1.3-py3-none-any.whl && rm /tmp/vllm_gptq-0.1.3-py3-none-any.whl`
 6. `python3 server.py`
 
 An example systemctl service file is provided in `other/local-llm.service`.

llm_server/config.py

@@ -22,7 +22,7 @@ config_required_vars = ['token_limit', 'concurrent_gens', 'mode', 'llm_middlewar
 mode_ui_names = {
     'oobabooga': ('Text Gen WebUI (ooba)', 'Blocking API url', 'Streaming API url'),
     'hf-textgen': ('Text Gen WebUI (ooba)', 'Blocking API url', 'Streaming API url'),
-    'vllm': ('Chat Completion', 'Reverse Proxy', 'N/A'),
+    'vllm': ('Text Gen WebUI (ooba)', 'Blocking API url', 'Streaming API url'),
 }
 
 

server.py

@@ -10,7 +10,7 @@ try:
     import vllm
 except ModuleNotFoundError as e:
     print('Could not import vllm-gptq:', e)
-    print('Please see vllm.md for install instructions')
+    print('Please see README.md for install instructions.')
     sys.exit(1)
 
 import config

templates/home.html

@@ -87,17 +87,12 @@
             <strong>Instructions:</strong>
             <ol>
                 <li>Set your API type to <kbd>{{ mode_name }}</kbd></li>
-                {% if not ws_client_api %}
-                <li>Set <kbd>Chat Completion Source</kbd> to <kbd>OpenAI</kbd>.</li>
-                {% endif %}
                 <li>Enter <kbd>{{ client_api }}</kbd> in the <kbd>{{ api_input_textbox }}</kbd> textbox.</li>
-                {% if ws_client_api %}
                 <li>Enter <kbd>{{ ws_client_api }}</kbd> in the <kbd>{{ streaming_input_textbox }}</kbd> textbox.
                 </li>
-                <li>If using a token, check the <kbd>Mancer AI</kbd> checkbox and enter your token in the <kbd>Mancer
+                <li>If you have a token, check the <kbd>Mancer AI</kbd> checkbox and enter your token in the <kbd>Mancer
                     API key</kbd> textbox.
                 </li>
-                {% endif %}
                 <li>Click <kbd>Connect</kbd> to test the connection.</li>
                 <li>Open your preset config and set <kbd>Context Size</kbd> to {{ context_size }}.</li>
                 <li>Follow this guide to get set up: <a href="https://rentry.org/freellamas" target="_blank">rentry.org/freellamas</a>