feat: enhance chat service with documentation indexing and improved Docker configuration

src/datacenter_docs/utils/llm_client.py

@@ -14,6 +14,7 @@ This client works with:
 import logging
 from typing import Any, AsyncIterator, Dict, List, Optional, Union, cast
 
+import httpx
 from openai import AsyncOpenAI
 from openai.types.chat import ChatCompletion, ChatCompletionChunk
 
@@ -79,8 +80,13 @@ class LLMClient:
         self.temperature = temperature if temperature is not None else settings.LLM_TEMPERATURE
         self.max_tokens = max_tokens or settings.LLM_MAX_TOKENS
 
-        # Initialize AsyncOpenAI client
-        self.client = AsyncOpenAI(base_url=self.base_url, api_key=self.api_key)
+        # Initialize AsyncOpenAI client with custom HTTP client (disable SSL verification for self-signed certs)
+        http_client = httpx.AsyncClient(verify=False, timeout=30.0)
+        self.client = AsyncOpenAI(
+            base_url=self.base_url,
+            api_key=self.api_key,
+            http_client=http_client
+        )
 
         logger.info(f"Initialized LLM client: base_url={self.base_url}, model={self.model}")