From 03110b4a80677377b41eda008aa45ef9b4fb077b Mon Sep 17 00:00:00 2001
From: retoor <retoor@molodetz.nl>
Date: Fri, 7 Mar 2025 17:28:58 +0100
Subject: [PATCH] New example, new feature.

---
 Makefile               |  6 ++++
 setup.cfg              |  3 ++
 src/ragent/__init__.py | 74 ++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 81 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index 2f151ee..85ccd6b 100644
--- a/Makefile
+++ b/Makefile
@@ -2,6 +2,7 @@ DEMO_REPLIKA = .venv/bin/ragent.demo_replika
 DEMO_DISCUSS = .venv/bin/ragent.demo_discuss 
 DEMO_BATCH_MESSAGES = .venv/bin/ragent.demo_batch_messages
 DEMO_TOOLS = .venv/bin/ragent.demo_tools
+DEMO_VISION = .venv/bin/ragent.demo_vision
 PIP = .venv/bin/pip 
 
 default:
@@ -29,3 +30,8 @@ demo_batch_messages:
 demo_tools:
 	@echo "Executing Tools Demo."
 	$(DEMO_TOOLS)
+
+demo_vision:
+	@echo "Executing Vision Demo."
+	$(DEMO_VISION)
+
diff --git a/setup.cfg b/setup.cfg
index b410ae5..ba28441 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -25,4 +25,7 @@ console_scripts =
     ragent.demo_replika = ragent.demo_replika:main
     ragent.demo_batch_messages = ragent.demo_batch_messages:main 
     ragent.demo_tools = ragent.demo_tools:main 
+    ragent.demo_vision = ragent.demo_vision:main 
+
+
 
diff --git a/src/ragent/__init__.py b/src/ragent/__init__.py
index 781a716..8c8a00e 100644
--- a/src/ragent/__init__.py
+++ b/src/ragent/__init__.py
@@ -37,6 +37,7 @@ import pathlib
 import logging
 import sys
 import os
+import re
 from typing import Any, Dict
 import json
 import inspect
@@ -221,6 +222,33 @@ class Agent:
 
         self.thread = self.client.beta.threads.create()
         log.debug(f"Created thread with name {self.thread.id} for assistant {self.assistant.id}.")
+   
+    def get_file_by_name(self, name: str):
+        for file in self.client.files.list().data:
+            if file.filename == str(name):
+                log.debug(f"Found file with name: {name} and id: {file.id}.")
+                return file
+        log.debug(f"File with name: {name} not found.")
+        return None
+
+
+
+    def get_or_create_file(self, path: str):
+        path = pathlib.Path(path)
+        files = self.client.files.list().data
+        file = self.get_file_by_name(path)
+        if not file:
+            log.debug(f"File with name: {path} not found. Creating...")
+            file = self.client.files.create(
+                file=open(path, "rb"),
+                purpose="assistants"
+            )
+            log.debug(f"Created file with name: {path} and id: {file.id}.")
+            return file.id
+        else:
+            log.debug(f"Found file with name: {path} and id: {file.id}.")
+        return file.id
+
 
     @property
     def _assistants(self):
@@ -334,8 +362,50 @@ class Agent:
 
         return function_schema
 
-    def communicate(self, message: str, role: str = "user"):
+    def extract_image_urls(self,text):
+        image_url_pattern = r'https?://\S+\.(?:png|jpg|jpeg|gif|bmp|webp|svg)(?:\?\S*)?'
+    
+        return re.findall(image_url_pattern, text, re.IGNORECASE)
+
+    def communicate_images(self, message:str):
+        messages = message 
+        if not isinstance(messages, list):
+            messages = [message]
+        
+        for message in messages:
+            if isinstance(message, dict):
+                message_role = message["role"]
+                message = message["content"]
+            else:
+                message_role = "user"
+
+            for image_path in self.extract_image_urls(message):
+                response = self.client.chat.completions.create(
+                    model="gpt-4o-mini",
+                    messages=[
+                        {
+                            "role": "user",
+                            "content": [
+                                {"type": "text", "text": "Describe the image in full detail, in a way that a human could understand."},
+                                {
+                                    "type": "image_url",
+                                    "image_url": {
+                                        "url": image_path,
+                                    },
+                                },
+                            ],
+                        }
+                    ],
+                )
+                response = response.choices[0].message.content
+                response = f"This is the description of the image from the url {image_path} i have mentioned: " + response
+                self.communicate(response,role="user",ignore_image_urls=True)
+         
+
+    def communicate(self, message: str, role: str = "user", ignore_image_urls:bool=False):
         log.debug(f"Sending message: {message} to assistant {self.assistant.id} in thread {self.thread.id}.")
+        if not ignore_image_urls:
+            self.communicate_images(message)
         messages = isinstance(message, list) and message or [message]
         for message in messages:
             if isinstance(message, dict):
@@ -415,4 +485,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
\ No newline at end of file
+    main()