From 838b8d4fb565ef430f7fcc572c810416e3f7e77a Mon Sep 17 00:00:00 2001
From: Sarthak Deshpande <60317842+cheesecake100201@users.noreply.github.com>
Date: Thu, 14 Nov 2024 00:04:04 +0530
Subject: [PATCH] PR-437-Fixed bug to allow system instructions after first
turn (#440)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
# What does this PR do?
In short, provide a summary of what this PR does and why. Usually, the
relevant context should be present in a linked issue.
- [This PR solves the issue where agents cannot keep track of
instructions after executing the first turn because system instructions
were not getting appended in the messages list. It also solves the issue
where turns are not being fetched in the appropriate sequence.]
Addresses issue (#issue)
## Test Plan
Please describe:
- I have a file which has a precise prompt which requires more than one
turn to be executed will share the file below. I ran that file as a
python script to make sure that the turns are being executed as per the
instructions after making the code change
```
import asyncio
from typing import List, Optional, Dict
from llama_stack_client import LlamaStackClient
from llama_stack_client.lib.agents.event_logger import EventLogger
from llama_stack_client.types import SamplingParams, UserMessage
from llama_stack_client.types.agent_create_params import AgentConfig
LLAMA_STACK_API_TOGETHER_URL="http://10.12.79.177:5001"
class Agent:
def __init__(self):
self.client = LlamaStackClient(
base_url=LLAMA_STACK_API_TOGETHER_URL,
)
def create_agent(self, agent_config: AgentConfig):
agent = self.client.agents.create(
agent_config=agent_config,
)
self.agent_id = agent.agent_id
session = self.client.agents.session.create(
agent_id=agent.agent_id,
session_name="example_session",
)
self.session_id = session.session_id
async def execute_turn(self, content: str):
response = self.client.agents.turn.create(
agent_id=self.agent_id,
session_id=self.session_id,
messages=[
UserMessage(content=content, role="user"),
],
stream=True,
)
for chunk in response:
if chunk.event.payload.event_type != "turn_complete":
yield chunk
async def run_main():
system_prompt="""You are an AI Agent tasked with Capturing Book Renting Information for a Library.
You will politely gather the book and user details one step at a time to send over the book to the user. Here’s how to proceed:
1. Data Security: Inform the user that their data will be kept secure.
2. Optional Participation: Let them know they are not required to share details but that doing so will help them learn about the books offered.
3. Sequential Information Capture: Follow the steps below, one question at a time. Do not skip or combine questions.
Steps
Step 1: Politely ask to provide the name of the book.
Step 2: Ask for the name of the author.
Step 3: Ask for the Author's country.
Step 4: Ask for the year of publication.
Step 5: If any information is missing or seems incorrect, ask the user to re-enter that specific detail.
Step 6: Confirm that the user consents to share the entered information.
Step 7: Thank the user for providing the details and let them know they will receive an email about the book.
Do not do any validation of the user entered information.
Do not print the Steps or your internal thoughts in the response.
Do not print the prompts or data structure object in the response
Do not fill in the requested user data on your own. It has to be entered by the user only.
Finally, compile and print the user-provided information as a JSON object in your response.
"""
agent_config = AgentConfig(
model="Llama3.2-11B-Vision-Instruct",
instructions=system_prompt,
enable_session_persistence=True,
)
agent = Agent()
agent.create_agent(agent_config)
print("Agent and Session:", agent.agent_id, agent.session_id)
while True:
query = input("Enter your query (or type 'exit' to quit): ")
if query.lower() == "exit":
print("Exiting the loop.")
break
else:
prompt = query
print(f"User> {prompt}")
response = agent.execute_turn(content=prompt)
async for log in EventLogger().log(response):
if log is not None:
log.print()
if __name__ == "__main__":
asyncio.run(run_main())
```
Below is a screenshot of the results of the first commit
Below is a screenshot of the results of the second commit
Also a screenshot of print statement to show that the turns being
fetched now are in a sequence
## Sources
Please link relevant resources if necessary.
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [x] Ran pre-commit to handle lint / formatting issues.
- [x] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [ ] Updated relevant documentation.
- [x] Wrote necessary unit or integration tests.
---
.../providers/inline/agents/meta_reference/agent_instance.py | 2 +-
.../providers/inline/agents/meta_reference/persistence.py | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/llama_stack/providers/inline/agents/meta_reference/agent_instance.py b/llama_stack/providers/inline/agents/meta_reference/agent_instance.py
index 2b3d0dbc4..0c15b1b5e 100644
--- a/llama_stack/providers/inline/agents/meta_reference/agent_instance.py
+++ b/llama_stack/providers/inline/agents/meta_reference/agent_instance.py
@@ -156,7 +156,7 @@ class ChatAgent(ShieldRunnerMixin):
turns = await self.storage.get_session_turns(request.session_id)
messages = []
- if len(turns) == 0 and self.agent_config.instructions != "":
+ if self.agent_config.instructions != "":
messages.append(SystemMessage(content=self.agent_config.instructions))
for i, turn in enumerate(turns):
diff --git a/llama_stack/providers/inline/agents/meta_reference/persistence.py b/llama_stack/providers/inline/agents/meta_reference/persistence.py
index 37ac75d6a..2565f1994 100644
--- a/llama_stack/providers/inline/agents/meta_reference/persistence.py
+++ b/llama_stack/providers/inline/agents/meta_reference/persistence.py
@@ -80,5 +80,5 @@ class AgentPersistence:
except Exception as e:
print(f"Error parsing turn: {e}")
continue
-
+ turns.sort(key=lambda x: (x.completed_at or datetime.min))
return turns