server: tests: embeddings, fixed prompt do not exceed n_batch, increa…

…se embedding timeout, reduce number of concurrent embeddings

examples/server/tests/features/embeddings.feature

@@ -9,7 +9,7 @@ Feature: llama.cpp server
     And   42 as server seed
     And   2 slots
     And   1024 as batch size
-    And   4096 KV cache size
+    And   2048 KV cache size
     And   embeddings extraction
     Then  the server is starting
     Then  the server is healthy
@@ -87,9 +87,8 @@ Feature: llama.cpp server
     Then the server is idle
     Then all embeddings are generated
 
-  @wip
   Scenario: All embeddings should be the same
-    Given 20 fixed prompts
+    Given 10 fixed prompts
     And   a model bert-bge-small
     Given concurrent OAI embedding requests
     Then the server is busy

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

@@ -292,9 +292,10 @@ def step_impl(context, n_ga_w):
 def step_prompt_passkey(context):
     context.prompt_passkey = context.text
 
+
 @step(u'{n_prompts:d} fixed prompts')
 def step_fixed_prompts(context, n_prompts):
-    context.prompts.extend([str(0)*1024 for i in range(n_prompts)])
+    context.prompts.extend([str(0)*(context.n_batch if context.n_batch is not None else 512) for i in range(n_prompts)])
     context.n_prompts = n_prompts
 
 
@@ -818,7 +819,8 @@ async def request_oai_embeddings(input,
                                         "input": input,
                                         "model": model,
                                     },
-                                    headers=headers) as response:
+                                    headers=headers,
+                                    timeout=3600) as response:
                 assert response.status == 200, f"received status code not expected: {response.status}"
                 assert response.headers['Access-Control-Allow-Origin'] == origin
                 assert response.headers['Content-Type'] == "application/json; charset=utf-8"