alihan/agents-course
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #406 from decipherIO/unit1-patch

Browse Source 
fix name 'SYSTEM_PROMPT' is undefined
This commit is contained in:
Sergio Paniego Blanco
2025-04-04 09:25:18 +02:00
committed by GitHub
parent bd639da244 46ca1f887e
commit 4ab322de57
1 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
units/en/unit1/dummy-agent-library.mdx
View File

@@ -94,7 +94,10 @@ This system prompt is a bit more complex than the one we saw earlier, but it alr
2. **Cycle instructions** (Thought → Action → Observation)
```
Answer the following questions as best you can. You have access to the following tools:
# This system prompt is a bit more complex and actually contains the function description already appended.
# Here we suppose that the textual description of the tools has already been appended.
SYSTEM_PROMPT = """Answer the following questions as best you can. You have access to the following tools:
get_weather: Get the current weather in a given location
@@ -103,13 +106,14 @@ Specifically, this json should have an `action` key (with the name of the tool t
The only values that should be in the "action" field are:
get_weather: Get the current weather in a given location, args: {"location": {"type": "string"}}
example use :
example use :
{{
"action": "get_weather",
"action_input": {"location": "New York"}
}}
ALWAYS use the following format:
Question: the input question you must answer
@@ -126,7 +130,7 @@ You must always end your output with the following format:
Thought: I now know the final answer
Final Answer: the final answer to the original input question
Now begin! Reminder to ALWAYS use the exact characters `Final Answer:` when you provide a definitive answer.
Now begin! Reminder to ALWAYS use the exact characters `Final Answer:` when you provide a definitive answer. """
```
Since we are running the "text_generation" method, we need to apply the prompt manually: