feat: Introduce LLM response caching and streaming, add application configuration, and enhance session data with progress and history tracking.

2026-01-24 12:52:35 +08:00
parent 162f5c4da4
commit fbbb5a2470
10 changed files with 1015 additions and 4 deletions
--- a/test.py
+++ b/test.py
@@ -7,7 +7,7 @@ client = openai.OpenAI(
 )

 response = client.chat.completions.create(
-    model="gemini-2.5-flash",
+    model="gemini-2.5-pro",
    messages=[{"role": "user", "content": "你好，请自我介绍"}]
 )
 print(response.choices[0].message.content)