From b4e73c7f19188007f5702471a9067a688dad4b56 Mon Sep 17 00:00:00 2001
From: "Timothy J. Baek" <timothyjrbeck@gmail.com>
Date: Mon, 21 Oct 2024 04:10:28 -0700
Subject: [PATCH] refac: convert_payload_openai_to_ollama

---
 backend/open_webui/utils/payload.py | 48 ++++++++++++++++++++++++++++-
 1 file changed, 47 insertions(+), 1 deletion(-)

diff --git a/backend/open_webui/utils/payload.py b/backend/open_webui/utils/payload.py
index 72aec6a6c..2789b942f 100644
--- a/backend/open_webui/utils/payload.py
+++ b/backend/open_webui/utils/payload.py
@@ -88,6 +88,50 @@ def apply_model_params_to_body_ollama(params: dict, form_data: dict) -> dict:
     return form_data
 
 
+def convert_messages_openai_to_ollama(messages: list[dict]) -> list[dict]:
+    ollama_messages = []
+
+    for message in messages:
+        # Initialize the new message structure with the role
+        new_message = {"role": message["role"]}
+
+        content = message.get("content", [])
+
+        # Check if the content is a string (just a simple message)
+        if isinstance(content, str):
+            # If the content is a string, it's pure text
+            new_message["content"] = content
+        else:
+            # Otherwise, assume the content is a list of dicts, e.g., text followed by an image URL
+            content_text = ""
+            images = []
+
+            # Iterate through the list of content items
+            for item in content:
+                # Check if it's a text type
+                if item.get("type") == "text":
+                    content_text += item.get("text", "")
+
+                # Check if it's an image URL type
+                elif item.get("type") == "image_url":
+                    img_url = item.get("image_url", {}).get("url", "")
+                    if img_url:
+                        images.append(img_url)
+
+            # Add content text (if any)
+            if content_text:
+                new_message["content"] = content_text.strip()
+
+            # Add images (if any)
+            if images:
+                new_message["images"] = images
+
+        # Append the new formatted message to the result
+        ollama_messages.append(new_message)
+
+    return ollama_messages
+
+
 def convert_payload_openai_to_ollama(openai_payload: dict) -> dict:
     """
     Converts a payload formatted for OpenAI's API to be compatible with Ollama's API endpoint for chat completions.
@@ -102,7 +146,9 @@ def convert_payload_openai_to_ollama(openai_payload: dict) -> dict:
 
     # Mapping basic model and message details
     ollama_payload["model"] = openai_payload.get("model")
-    ollama_payload["messages"] = openai_payload.get("messages")
+    ollama_payload["messages"] = convert_messages_openai_to_ollama(
+        openai_payload.get("messages")
+    )
     ollama_payload["stream"] = openai_payload.get("stream", False)
 
     # If there are advanced parameters in the payload, format them in Ollama's options field