refactor(pm4py): changing API interfacing for OpenAI

pm4py/algo/querying/llm/connectors/openai.py

@@ -1,27 +1,57 @@
 from enum import Enum
 from pm4py.util import exec_utils
 from typing import Optional, Dict, Any
+import base64
+import requests
 from pm4py.util import constants
 
 
 class Parameters(Enum):
     API_KEY = "api_key"
     OPENAI_MODEL = "openai_model"
+    IMAGE_PATH = "image_path"
 
 
-def apply(query: str, parameters: Optional[Dict[Any, Any]] = None) -> str:
+def encode_image(image_path):
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode('utf-8')
+
+
+def apply(prompt: str, parameters: Optional[Dict[Any, Any]] = None) -> str:
     if parameters is None:
         parameters = {}
 
     api_key = exec_utils.get_param_value(Parameters.API_KEY, parameters, constants.OPENAI_API_KEY)
-    model = exec_utils.get_param_value(Parameters.OPENAI_MODEL, parameters, constants.OPENAI_DEFAULT_MODEL)
-
-    import openai
-
-    client = openai.OpenAI(api_key=api_key)
-
-    message = {"role": "user", "content": query}
-
-    response = client.chat.completions.create(model=model, messages=[message])
-
-    return response.choices[0].message.content
+    image_path = exec_utils.get_param_value(Parameters.IMAGE_PATH, parameters, None)
+    model = exec_utils.get_param_value(Parameters.OPENAI_MODEL, parameters,
+                                       constants.OPENAI_DEFAULT_MODEL if image_path is None else constants.OPENAI_DEFAULT_VISION_MODEL)
+
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {api_key}"
+    }
+
+    payload = {
+        "model": model,
+        "messages": [
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "text",
+                        "text": prompt
+                    }
+                ]
+            }
+        ]
+    }
+
+    if image_path is not None:
+        base64_image = encode_image(image_path)
+        payload["messages"][0]["content"].append(
+            {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{base64_image} "}})
+        payload["max_tokens"] = 4096
+
+    response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload).json()
+
+    return response["choices"][0]["message"]["content"]

pm4py/llm.py

@@ -1,11 +1,11 @@
-import duckdb
 import pandas as pd
 from pm4py.objects.log.obj import EventLog, EventStream, Trace
 from typing import Union, Optional, Dict, Tuple, Any
 from pm4py.utils import get_properties, constants
 from pm4py.utils import __event_log_deprecation_warning
 from pm4py.objects.ocel.obj import OCEL
 from sqlite3 import Connection as SQ3_Connection
+from copy import copy
 from pm4py.objects.petri_net.obj import PetriNet, Marking
 
 
@@ -25,7 +25,7 @@ def openai_query(prompt: str, api_key: Optional[str] = None, openai_model: Optio
         resp = pm4py.llm.openai_query('what is the result of 3+3?', api_key="sk-382393", openai_model="gpt-3.5-turbo")
         print(resp)
     """
-    parameters = {}
+    parameters = copy(kwargs) if kwargs is not None else {}
     if api_key is not None:
         parameters["api_key"] = api_key
     if openai_model is not None: