short prompt

app.py

@@ -772,47 +772,39 @@ First check if you can answer the question by yourself without the need for a to
 You also have access to a set of tools, which you can use to answer the question, if you can't answer the question directly. The available tools are:
 {tool_descriptions}
 
-If there is a file (image, audio, or video) attached to the question, you should use the process_attachment tool to process it and follow the instructions below:
- - For audio or video attachments, the process_attachment tool will transcribe the audio and return the transcript, which you can use to answer the question. 
- -  For image attachments, the process_attachment tool will return a base64 encoded string of the image. You can use this encoded information to provide answer.
-
 If the question is related to sports, awards, historical facts or similar topic that can be answered from wikipedia, you should use the 'wikipedia_and_generalknowledge_search', if the question is based on current events or news kind then you can utilize the tool 'current_events_news_search_tool' to fetch relevant page information and answer from it. 
 You must not use multiple tools in a single call. Don't hallucinate.
 
+Instructions to follow for YOUR FINAL ANSWER:
+- Don't include explanations, thoughts, or tool calls in YOUR FINAL ANSWER.
+- YOUR FINAL ANSWER should be a single value (number, string, or comma-separated list).
+- If your example thought and Final Answer is something like 'Thought:Final Answer: The country with the least number of athletes at the 1928 Summer Olympics was Luxembourg, which had only 2 athletes.' then your output should be just: 'Luxembourg'
 
-For each question, follow this format:
-
-Question: the input question you must answer
-Thought: your reasoning about what to do next
-Action: the action to take, must be one of the tools. If no relevant tools, answer the question directly.
-Action Input: the input to the action
-Observation: the result of the action
-... (repeat Thought/Action/Action Input/Observation as needed)
-Final Answer: the answer to the original question, as concise as possible (number, short string, or comma-separated list, no extra explanation).
 
 **Examples:**
 Q: Which country had the least number of athletes at the 1928 Summer Olympics?
 Final Answer: Luxembourg
 
-Q: How many albums did the band release?
-Final Answer: 5
-
 Q: List the top 3 programming languages.
 Final Answer: Python, JavaScript, Java
 
 Q: What is the maximum number os birds in the video https://www.youtube.com/watch?v=example?
 Final Answer: 12
 
-Rules for YOUR FINAL ANSWER:
-- Don't include explanations, thoughts, or tool calls in YOUR FINAL ANSWER.
-- YOUR FINAL ANSWER should be a single value (number, string, or comma-separated list).
-- If your example thought and Final Answer is something like 'Thought:Final Answer: The country with the least number of athletes at the 1928 Summer Olympics was Luxembourg, which had only 2 athletes.' then your output should be just: 'Luxembourg'
 
 If after 12 iterations also a tool usage is not useful then try to answer directly based on your knowledge. If you cannot answer then just say "no_answer" as YOUR FINAL ANSWER.
-
 """
 # If your final answer is something like 'there were 5 studio albums published between 2000 and 2009' then modify YOUR FINAL ANSWER as: '5' 
 # If your final answer is something like 'b, e' then YOUR FINAL ANSWER be: 'b, e'
+# For each question, follow this format:
+
+# Question: the input question you must answer
+# Thought: your reasoning about what to do next
+# Action: the action to take, must be one of the tools. If no relevant tools, answer the question directly.
+# Action Input: the input to the action
+# Observation: the result of the action
+# ... (repeat Thought/Action/Action Input/Observation as needed)
+# Final Answer: the answer to the original question, as concise as possible (number, short string, or comma-separated list, no extra explanation).
 
 
 # system_prompt = f"""
@@ -867,7 +859,7 @@ chat_llm = ChatHuggingFace(llm=llm)
 chat_llm = ChatOpenAI(
     openai_api_key=OPENAI_KEY,
     model_name=OPENAI_MODEL,
-    temperature=0.05,
+    temperature=0.1,
     # max_tokens=10
 )