feat : support for local openai based api

README.md

@@ -222,7 +222,11 @@ ip a | grep "inet " | grep -v 127.0.0.1 | awk '{print $2}' | cut -d/ -f1
 
 Note: For Windows or macOS, use ipconfig or ifconfig respectively to find the IP address.
 
-Clone the repository and then, run the script `stream_llm.py` in `server/`
+**If you wish to use openai based provider follow the *Run with an API*  section. vLLM**
+
+Make sure ollama is installed (Currently our script only support ollama)
+
+Run our server script.
 
 ```sh
 python3 server_ollama.py --model "deepseek-r1:32b"
@@ -232,8 +236,6 @@ python3 server_ollama.py --model "deepseek-r1:32b"
 
 Now on your personal computer:
 
-Clone the repository.
-
 Change the `config.ini` file to set the `provider_name` to `server` and `provider_model` to `deepseek-r1:14b`.
 Set the `provider_server_address` to the ip address of the machine that will run the model.
 
@@ -254,18 +256,20 @@ python3 main.py
 
 ## **Run with an API**  
 
-Clone the repository.
-
 Set the desired provider in the `config.ini`
 
 ```sh
 [MAIN]
 is_local = False
 provider_name = openai
-provider_model = gpt4-o
-provider_server_address = 127.0.0.1:5000 # can be set to anything, not used
+provider_model = gpt4o
+provider_server_address = 127.0.0.1:5000
 ```
 
+Set `is_local` to True if using a local openai-based api.
+
+Change the IP address if your openai-based api run on your own server.
+
 Run the assistant:
 
 ```sh

main.py

@@ -22,12 +22,10 @@ def handleInterrupt(signum, frame):
 def main():
     signal.signal(signal.SIGINT, handler=handleInterrupt)
 
-    if config.getboolean('MAIN', 'is_local'):
-        provider = Provider(config["MAIN"]["provider_name"], config["MAIN"]["provider_model"], config["MAIN"]["provider_server_address"])
-    else:
     provider = Provider(provider_name=config["MAIN"]["provider_name"],
                         model=config["MAIN"]["provider_model"],
-                                   server_address=config["MAIN"]["provider_server_address"])
+                        server_address=config["MAIN"]["provider_server_address"],
+                        is_local=config.getboolean('MAIN', 'is_local'))
 
     browser = Browser(create_driver(), headless=config.getboolean('MAIN', 'headless_browser'))
 

sources/llm_provider.py

@@ -15,9 +15,10 @@ import httpx
 from sources.utility import pretty_print, animate_thinking
 
 class Provider:
-    def __init__(self, provider_name, model, server_address = "127.0.0.1:5000"):
+    def __init__(self, provider_name, model, server_address = "127.0.0.1:5000", is_local=False):
         self.provider_name = provider_name.lower()
         self.model = model
+        self.is_local = is_local
         self.server = self.check_address_format(server_address)
         self.available_providers = {
             "ollama": self.ollama_fn,
@@ -169,11 +170,16 @@ class Provider:
         """
         Use openai to generate text.
         """
+        if self.is_local:
+            print("Using local OpenAI server")
+            client = OpenAI(api_key=self.api_key, base_url=base_url)
+        else:
+            print("Using OpenAI API")
             client = OpenAI(api_key=self.api_key)
         try:
             response = client.chat.completions.create(
                 model=self.model,
-                messages=history
+                messages=history,
             )
             thought = response.choices[0].message.content
             if verbose: