Increase embedding/LLM call timeout

app.py

@@ -181,7 +181,7 @@ def generate_embeddings(texts: list[str]) -> list[list[float]]:
     }
     try:
         resp = http_requests.post(
-            EMBEDDING_ENDPOINT_URL, headers=headers, json=payload, timeout=60,
+            EMBEDDING_ENDPOINT_URL, headers=headers, json=payload, timeout=120,
         )
         resp.raise_for_status()
         data = resp.json()
@@ -278,7 +278,7 @@ def call_llm(prompt: str) -> dict:
         "top_p": LLM_TOP_P,
     }
     try:
-        resp = http_requests.post(LLM_ENDPOINT_URL, headers=headers, json=payload, timeout=60)
+        resp = http_requests.post(LLM_ENDPOINT_URL, headers=headers, json=payload, timeout=None)
         resp.raise_for_status()
         data = resp.json()
         content = data["choices"][0]["message"]["content"].strip()