Refactor Dockerfile and workflow to include version pattern for relea…

.github/workflows/publish_image.yaml

@@ -35,6 +35,10 @@ jobs:
         uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
         with:
           images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=branch,pattern=release/v(?<version>\d+\.\d+\.\d+),group=version
+
 
       - name: Build and push Docker image
         id: push

README.md

@@ -1 +1,14 @@
-# openai_api_mock
+# OpenAI API server mockup
+This is a simple fastapi based server mock that implements the OpenAI API.
+
+Available endpoints:
+- /v1/chat/completion
+
+Instead of running a LLM model to generate completions, it simply returns a response generated by surrogate models. Available surrogate models are:
+- "yes_no": returns random "yes" or "no" response
+- "lorem_ipsum": returns random "lorem ipsum" text
+
+## Run via docker:
+```bash
+docker pull ghcr.io/hummerichsander/openai_api_server_mock:v ... # replace ... with the latest version
+```

sandbox.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -11,7 +11,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -20,41 +20,48 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
     "chat_completion = client.chat.completions.create(\n",
     "    model=\"yes_no\",\n",
     "    messages=[\n",
     "        {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n",
-    "        {\"role\": \"user\", \"content\": \"was geht ab?\"}\n",
+    "        {\"role\": \"user\", \"content\": \"Is the sky blue?\"}\n",
     "    ],\n",
-    "    max_tokens=3,\n",
+    "    max_tokens=1,\n",
     "    logprobs=True,\n",
     "    top_logprobs=3,\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Choice(finish_reason='stop', index=0, logprobs=ChoiceLogprobs(content=[ChatCompletionTokenLogprob(token='No', bytes=None, logprob=-0.07924283253114733, top_logprobs=[TopLogprob(token='No', bytes=None, logprob=-0.10242905896332069), TopLogprob(token='Yes', bytes=None, logprob=-1.2416030261034656), TopLogprob(token='No', bytes=None, logprob=-0.8485894646489763)])], refusal=None), message=ChatCompletionMessage(content='No', refusal=None, role='assistant', function_call=None, tool_calls=None, name=None))]"
+       "[Choice(finish_reason='stop', index=0, logprobs=ChoiceLogprobs(content=[ChatCompletionTokenLogprob(token='No', bytes=None, logprob=-0.4558056105339685, top_logprobs=[TopLogprob(token='Yes', bytes=None, logprob=-2.1267604392490442), TopLogprob(token='No', bytes=None, logprob=-0.7188313398698458), TopLogprob(token='Yes', bytes=None, logprob=-3.7428107344910946)])], refusal=None), message=ChatCompletionMessage(content='Yes', refusal=None, role='assistant', function_call=None, tool_calls=None, name=None))]"
       ]
      },
-     "execution_count": 31,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "chat_completion.choices"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -73,7 +80,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.12.1"
   }
  },
  "nbformat": 4,