Update main.py

main.py

@@ -689,15 +689,15 @@ def investment(queries, query_results, other_info_results):
     encoding = tiktoken.encoding_for_model("gpt-3.5-turbo")
     sys_prompt_token_size = len(encoding.encode(sys_prompt))
 
-    max_model_tokens = 6000
-    max_chunk_size = 6000  # Adjust to leave more buffer space
+    max_model_tokens = 7000
+    max_chunk_size = 7000  # Adjust to leave more buffer space
 
     chunks = split_into_chunks(message, token_limit=max_chunk_size)
 
     model = "meta-llama/llama-3-70b-instruct:nitro"
     responses = []
     tokens_used = 0
-    max_tokens_per_minute = 6000
+    max_tokens_per_minute = 7000
 
     for chunk in chunks:
         chunk_token_size = len(encoding.encode(chunk))