fix: linting issues

.pre-commit-config.yaml

@@ -21,5 +21,4 @@ repos:
   - repo: https://github.com/python-poetry/poetry
     rev: "1.4.0" # add version here
     hooks:
-      - id: poetry-check
-      - id: poetry-lock
+      - id: poetry-check

examples/azure-openai/azure-universal.py

@@ -1,17 +1,22 @@
 import os
+
+from dotenv import load_dotenv
 from openai import AzureOpenAI
+
 from javelin_sdk import JavelinClient, JavelinConfig
-from dotenv import load_dotenv
 
 load_dotenv()
 
+
 def initialize_client():
     """
     Creates the AzureOpenAI client and registers it with Javelin.
     Returns the AzureOpenAI client object if successful, else None.
     """
-    javelin_api_key = os.getenv("JAVELIN_API_KEY") # add your javelin api key here
-    azure_openai_api_key = os.getenv("AZURE_OPENAI_API_KEY") # Add your Azure OpenAI key
+    javelin_api_key = os.getenv("JAVELIN_API_KEY")  # add your javelin api key here
+    azure_openai_api_key = os.getenv(
+        "AZURE_OPENAI_API_KEY"
+    )  # Add your Azure OpenAI key
 
     if not javelin_api_key:
         print("Error: JAVELIN_API_KEY is not set!")
@@ -29,13 +34,13 @@ def initialize_client():
         # Typically "2023-07-01-preview" or a more recent version
         api_version="2023-07-01-preview",
         azure_endpoint="https://javelinpreview.openai.azure.com",
-        api_key=azure_openai_api_key
+        api_key=azure_openai_api_key,
     )
 
     # Initialize the Javelin client and register the Azure client
     config = JavelinConfig(javelin_api_key=javelin_api_key)
     javelin_client = JavelinClient(config)
-    rout_name = "azureopenai_univ" # Define the unversal route name
+    rout_name = "azureopenai_univ"  # Define the unversal route name
     javelin_client.register_azureopenai(azure_client, route_name=rout_name)
 
     return azure_client
@@ -49,8 +54,7 @@ def get_chat_completion_sync(azure_client, messages):
     """
 
     response = azure_client.chat.completions.create(
-        model="gpt-4",  # Adjust to your Azure deployment name
-        messages=messages
+        model="gpt-4", messages=messages  # Adjust to your Azure deployment name
     )
     return response.to_json()
 
@@ -63,7 +67,7 @@ def get_chat_completion_stream(azure_client, messages):
     response = azure_client.chat.completions.create(
         model="gpt-4",  # Adjust to your Azure deployment name
         messages=messages,
-        stream=True
+        stream=True,
     )
 
     # Accumulate streamed text
@@ -79,7 +83,6 @@ def get_chat_completion_stream(azure_client, messages):
     return "".join(streamed_text)
 
 
-
 def get_text_completion(azure_client, prompt):
     """
     Demonstrates Azure text completion (non-chat).
@@ -90,7 +93,7 @@ def get_text_completion(azure_client, prompt):
         model="gpt-4o",  # Adjust to your actual Azure completions model name
         prompt=prompt,
         max_tokens=50,
-        temperature=0.7
+        temperature=0.7,
     )
     return response.to_json()
 
@@ -102,7 +105,7 @@ def get_embeddings(azure_client, text):
     """
     response = azure_client.embeddings.create(
         model="text-embedding-ada-002",  # Adjust to your embeddings model name
-        input=text
+        input=text,
     )
     return response.to_json()
 
@@ -115,9 +118,7 @@ def main():
         return
 
     # Example chat messages
-    messages = [
-        {"role": "user", "content": "say hello"}
-    ]
+    messages = [{"role": "user", "content": "say hello"}]
 
     # 1) Chat Completion (Synchronous)
     try:

examples/azure-openai/langchain_azure_universal.py

@@ -1,10 +1,10 @@
 import os
-from dotenv import load_dotenv
 
-from langchain_openai import AzureChatOpenAI
-from langchain.schema import HumanMessage, SystemMessage, AIMessage
+from dotenv import load_dotenv
 from langchain.callbacks.base import BaseCallbackHandler
 from langchain.callbacks.manager import CallbackManager
+from langchain.schema import HumanMessage, SystemMessage
+from langchain_openai import AzureChatOpenAI
 
 #
 # 1) Keys and Route Setup
@@ -13,10 +13,13 @@
 load_dotenv()
 azure_openai_api_key = os.getenv("AZURE_OPENAI_API_KEY")
 javelin_api_key = os.getenv("JAVELIN_API_KEY")
-base_url = os.getenv("JAVELIN_BASE_URL", "https://api.javelin.live")  # Default to generic base URL
+base_url = os.getenv(
+    "JAVELIN_BASE_URL", "https://api.javelin.live"
+)  # Default to generic base URL
 
 # The name of your Azure deployment (e.g., "gpt-4")
-# or whatever you’ve set in Azure. Must also match x-javelin-model if Javelin expects that.
+# or whatever you’ve set in Azure. Must also match x-javelin-model if
+# Javelin expects that.
 model_choice = "gpt-4"
 
 # Javelin route name, as registered in your javelin route dashboard
@@ -32,7 +35,7 @@
     openai_api_key=azure_openai_api_key,
     # Provide your actual API version
     api_version="2024-08-01-preview",
-    # The base_url is Javelin’s universal route 
+    # The base_url is Javelin’s universal route
     base_url=f"{base_url}/v1/azureopenai/deployments/gpt-4/",
     validate_base_url=False,
     verbose=True,
@@ -42,9 +45,10 @@
         "x-javelin-model": model_choice,
         "x-javelin-provider": "https://javelinpreview.openai.azure.com/openai",
     },
-    streaming=False  # Non-streaming
+    streaming=False,  # Non-streaming
 )
 
+
 #
 # 3) Single-Turn Invoke (Non-Streaming)
 #
@@ -60,28 +64,32 @@ def invoke_non_streaming(question: str) -> str:
     # The response is usually an AIMessage. Return its content.
     return response.content
 
+
 #
 # 4) Single-Turn Streaming
 #    We'll create a new LLM with streaming=True, plus a callback handler.
 #
 
+
 class StreamCallbackHandler(BaseCallbackHandler):
     """
     Collects tokens as they are streamed, so we can return the final text.
     """
+
     def __init__(self):
         self.tokens = []
 
     def on_llm_new_token(self, token: str, **kwargs) -> None:
         self.tokens.append(token)
 
+
 def invoke_streaming(question: str) -> str:
     """
     Sends a single user message to the LLM (streaming=True).
     Collects the tokens from the callback and returns them as a string.
     """
     callback_handler = StreamCallbackHandler()
-    callback_manager = CallbackManager([callback_handler])
+    CallbackManager([callback_handler])
 
     llm_streaming = AzureChatOpenAI(
         openai_api_key=azure_openai_api_key,
@@ -95,16 +103,17 @@ def invoke_streaming(question: str) -> str:
             "x-javelin-model": model_choice,
             "x-javelin-provider": "https://javelinpreview.openai.azure.com/openai",
         },
-        streaming=True,           # <-- streaming on
-        callbacks=[callback_handler]  # <-- our custom callback
+        streaming=True,  # <-- streaming on
+        callbacks=[callback_handler],  # <-- our custom callback
     )
 
     messages = [HumanMessage(content=question)]
-    response = llm_streaming.invoke(messages)
+    llm_streaming.invoke(messages)
     # We could check response, but it's usually an AIMessage with partial content
     # The real text is captured in the callback tokens
     return "".join(callback_handler.tokens)
 
+
 #
 # 5) Conversation Demo
 #
@@ -117,7 +126,7 @@ def conversation_demo():
 
     conversation_llm = llm_non_streaming
 
-    # Start with a system message 
+    # Start with a system message
     messages = [SystemMessage(content="You are a friendly assistant.")]
     user_q1 = "Hello, how are you?"
     messages.append(HumanMessage(content=user_q1))
@@ -133,12 +142,13 @@ def conversation_demo():
 
     return "Conversation done!"
 
+
 #
 # 6) Main Function
 #
 def main():
     print("=== LangChain AzureOpenAI Example ===")
-    
+
     # 1) Single-turn Non-Streaming Invoke
     print("\n--- Single-turn Non-Streaming Invoke ---")
     question_a = "What is the capital of France?"
@@ -150,7 +160,7 @@ def main():
             print(f"Question: {question_a}\nAnswer: {response_a}")
     except Exception as e:
         print(f"Error in non-streaming invoke: {e}")
-    
+
     # 2) Single-turn Streaming Invoke
     print("\n--- Single-turn Streaming Invoke ---")
     question_b = "Tell me a quick joke."
@@ -162,15 +172,16 @@ def main():
             print(f"Question: {question_b}\nStreamed Answer: {response_b}")
     except Exception as e:
         print(f"Error in streaming invoke: {e}")
-    
+
     # 3) Multi-turn Conversation Demo
     print("\n--- Simple Conversation Demo ---")
     try:
         conversation_demo()
     except Exception as e:
         print(f"Error in conversation demo: {e}")
-    
+
     print("\n=== All done! ===")
-
+
+
 if __name__ == "__main__":
     main()