Add "/chat/completions" as alias for "/v1/chat/completions"

examples/server/server.cpp

@@ -2927,9 +2927,7 @@ int main(int argc, char **argv)
                 res.set_content(models.dump(), "application/json; charset=utf-8");
             });
 
-
+    const auto chat_completions = [&llama, &validate_api_key, &sparams](const httplib::Request &req, httplib::Response &res)
-    // TODO: add mount point without "/v1" prefix -- how?
-    svr.Post("/v1/chat/completions", [&llama, &validate_api_key, &sparams](const httplib::Request &req, httplib::Response &res)
     {
         res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
         if (!validate_api_key(req, res)) {
@@ -3007,7 +3005,10 @@ int main(int argc, char **argv)
 
             res.set_chunked_content_provider("text/event-stream", chunked_content_provider, on_complete);
         }
-            });
+    };
+
+    svr.Post("/chat/completions", chat_completions);
+    svr.Post("/v1/chat/completions", chat_completions);
  
     svr.Post("/infill", [&llama, &validate_api_key](const httplib::Request &req, httplib::Response &res)
             {

examples/server/tests/features/parallel.feature

@@ -53,6 +53,28 @@ Feature: Parallel
       | disabled  | 128       |
       | enabled   | 64        |
 
+  Scenario Outline: Multi users OAI completions compatibility no v1
+    Given a system prompt You are a writer.
+    And   a model tinyllama-2
+    Given a prompt:
+      """
+      Write a very long book.
+      """
+    And a prompt:
+      """
+      Write another a poem.
+      """
+    And <n_predict> max tokens to predict
+    And streaming is <streaming>
+    Given concurrent OAI completions requests no v1
+    Then the server is busy
+    Then the server is idle
+    Then all prompts are predicted with <n_predict> tokens
+    Examples:
+      | streaming | n_predict |
+      | disabled  | 128       |
+      | enabled   | 64        |
+
   Scenario:  Multi users with total number of tokens to predict exceeds the KV Cache size #3969
     Given a prompt:
       """

examples/server/tests/features/steps/steps.py

@@ -222,6 +222,7 @@ async def step_oai_chat_completions(context, api_error):
     completion = await oai_chat_completions(context.prompts.pop(),
                                             context.system_prompt,
                                             context.base_url,
+                                            '/v1/chat',
                                             False,
                                             model=context.model if hasattr(context, 'model') else None,
 
@@ -279,6 +280,28 @@ async def step_oai_chat_completions(context):
                                          # user_prompt is inserted automatically
                                          context.system_prompt,
                                          context.base_url,
+                                         '/v1/chat/completions',
+                                         True,  # async_client
+                                         model=context.model
+                                         if hasattr(context, 'model') else None,
+                                         n_predict=context.n_predict
+                                         if hasattr(context, 'n_predict') else None,
+                                         enable_streaming=context.enable_streaming
+                                         if hasattr(context, 'enable_streaming') else None,
+                                         server_seed=context.server_seed
+                                         if hasattr(context, 'server_seed') else None,
+                                         user_api_key=context.user_api_key
+                                         if hasattr(context, 'user_api_key') else None)
+
+
+@step(u'concurrent OAI completions requests no v1')
+@async_run_until_complete
+async def step_oai_chat_completions(context):
+    await concurrent_completion_requests(context, oai_chat_completions,
+                                         # user_prompt is inserted automatically
+                                         context.system_prompt,
+                                         context.base_url,
+                                         '/chat/completions',
                                          True,  # async_client
                                          model=context.model
                                          if hasattr(context, 'model') else None,
@@ -449,6 +472,7 @@ async def request_completion(prompt,
 async def oai_chat_completions(user_prompt,
                                system_prompt,
                                base_url,
+                               base_path,
                                async_client,
                                debug=False,
                                model=None,
@@ -489,7 +513,7 @@ async def oai_chat_completions(user_prompt,
         origin = 'llama.cpp'
         headers = {'Authorization': f'Bearer {user_api_key}', 'Origin': origin}
         async with aiohttp.ClientSession() as session:
-            async with session.post(f'{base_url}/v1/chat/completions',
+            async with session.post(f'{base_url}{base_path}',
                                     json=payload,
                                     headers=headers) as response:
                 if enable_streaming:
@@ -531,7 +555,7 @@ async def oai_chat_completions(user_prompt,
     else:
         try:
             openai.api_key = user_api_key
-            openai.api_base = f'{base_url}/v1/chat'
+            openai.api_base = f'{base_url}{base_path}'
             chat_completion = openai.Completion.create(
                 messages=payload['messages'],
                 model=model,