mirror of
https://github.com/qdrant/landing_page.git
synced 2026-10-04 10:28:29 +02:00
docs: OpenAI Agents integration update (#1608)
Signed-off-by: Anush008 <anushshetty90@gmail.com>
This commit is contained in:
Anush
@@ -34,6 +34,7 @@ aliases: ["/documentation/frameworks/memgpt/"]
|
||||
| [Mirror Security](/documentation/frameworks/mirror-security/) | Python framework for vector encryption and access control. |
|
||||
| [Mem0](/documentation/frameworks/mem0/) | Self-improving memory layer for LLM applications, enabling personalized AI experiences. |
|
||||
| [Neo4j GraphRAG](/documentation/frameworks/neo4j-graphrag/) | Package to build graph retrieval augmented generation (GraphRAG) applications using Neo4j and Python. |
|
||||
| [OpenAI Agents](/documentation/frameworks/openai-agents/) | Python framework for managing multiple AI agents that can work together. |
|
||||
| [Pandas-AI](/documentation/frameworks/pandas-ai/) | Python library to query/visualize your data (CSV, XLSX, PostgreSQL, etc.) in natural language |
|
||||
| [Ragbits](/documentation/frameworks/ragbits/) | Python package that offers essential "bits" for building powerful Retrieval-Augmented Generation (RAG) applications. |
|
||||
| [Rig-rs](/documentation/frameworks/rig-rs/) | Rust library for building scalable, modular, and ergonomic LLM-powered applications. |
|
||||
@@ -42,7 +43,6 @@ aliases: ["/documentation/frameworks/memgpt/"]
|
||||
| [Solon](/documentation/frameworks/solon/) | A lightweight, high-performance Java enterprise framework |
|
||||
| [Spring AI](/documentation/frameworks/spring-ai/) | Java AI framework for building with Spring design principles such as portability and modular design. |
|
||||
| [Superduper](/documentation/frameworks/superduper/) | Framework for building flexible, compositional AI apps which may be applied directly to databases. |
|
||||
| [Swarm](/documentation/frameworks/swarm/) | Python framework for managing multiple AI agents that can work together. |
|
||||
| [Sycamore](/documentation/frameworks/sycamore/) | Document processing engine for ETL, RAG, LLM-based applications, and analytics on unstructured data. |
|
||||
| [Testcontainers](/documentation/frameworks/testcontainers/) | Framework for providing throwaway, lightweight instances of systems for testing |
|
||||
| [txtai](/documentation/frameworks/txtai/) | Python library for semantic search, LLM orchestration and language model workflows. |
|
||||
|
||||
@@ -0,0 +1,129 @@
|
||||
---
|
||||
title: OpenAI Agents
|
||||
aliases: [ /documentation/frameworks/swarm/ ]
|
||||
---
|
||||
|
||||
# OpenAI Agents
|
||||
|
||||
[OpenAI Agents](https://github.com/openai/openai-agents-python) is a Python framework to build agentic AI apps in a lightweight, easy-to-use package with very few abstractions. It's a production-ready upgrade of the experimental framework, [Swarm](https://github.com/openai/swarm).
|
||||
|
||||
## Getting Started
|
||||
|
||||
To start using OpenAI Agents, follow these steps:
|
||||
|
||||
- Install the package
|
||||
|
||||
```bash
|
||||
pip install openai-agents
|
||||
```
|
||||
|
||||
- Set up your OpenAI API key
|
||||
|
||||
```bash
|
||||
export OPENAI_API_KEY="<YOUR_KEY>"
|
||||
```
|
||||
|
||||
## How It Works
|
||||
|
||||
The Agents SDK has a very small set of primitives:
|
||||
|
||||
- `Agents`, which are LLMs equipped with instructions and tools
|
||||
- `Handoffs`, which allow agents to delegate to other agents for specific tasks
|
||||
- `Guardrails`, which enable the inputs to agents to be validated
|
||||
|
||||
Used with Python, these building blocks make it easy to create real-world apps with tool-agent interactions and minimal learning curve. Plus, the SDK also includes tracing to help you debug, evaluate, and fine-tune your agent workflows.
|
||||
|
||||
## Creating Your First Agents
|
||||
|
||||
Here’s a basic example of three agents:
|
||||
|
||||
- Triage Agent: Acts as the initial point of contact. It analyzes the user's question and decides whether to route it to a specialized agent.
|
||||
- Math Tutor: A specialist agent designed to help with math-related questions.
|
||||
- History Tutor: A specialist agent focused on historical topics.
|
||||
|
||||
```python
|
||||
from agents import Agent, Runner
|
||||
|
||||
|
||||
math_tutor_agent = Agent(
|
||||
name="Math Tutor",
|
||||
handoff_description="Specialist agent for math questions",
|
||||
instructions="You provide help with math problems. Explain your reasoning at each step and include examples",
|
||||
)
|
||||
|
||||
history_tutor_agent = Agent(
|
||||
name="History Tutor",
|
||||
handoff_description="Specialist agent for historical questions",
|
||||
instructions="You provide assistance with historical queries. Explain important events and context clearly.",
|
||||
)
|
||||
|
||||
triage_agent = Agent(
|
||||
name="Triage Agent",
|
||||
instructions="You determine which agent to use based on the user's homework question",
|
||||
handoffs=[history_tutor_agent, math_tutor_agent],
|
||||
)
|
||||
|
||||
# Run the interaction
|
||||
result = Runner.run_sync(triage_agent, "I want some help with WW1.")
|
||||
print(result.final_output)
|
||||
```
|
||||
|
||||
## Integrating with Qdrant
|
||||
|
||||
You can connect agents to retrieve or ingest data into a Qdrant collection. Thereby building your knowledge base. Here’s how to enable an agent to retrieve information from Qdrant.
|
||||
|
||||
Assume you have a Qdrant [collection created](https://qdrant.tech/documentation/concepts/collections/#create-a-collection) using the `"text-embedding-3-small"` model. The payload structure includes a `text` field for knowledge storage.
|
||||
|
||||
```python
|
||||
import qdrant_client
|
||||
from openai import OpenAI
|
||||
from agents import Agent, function_tool
|
||||
|
||||
# Initialize clients
|
||||
openai_client = OpenAI()
|
||||
qdrant = qdrant_client.QdrantClient(host="localhost")
|
||||
|
||||
# Configuration
|
||||
EMBEDDING_MODEL = "text-embedding-3-small"
|
||||
COLLECTION_NAME = "help_center"
|
||||
LIMIT = 5
|
||||
SCORE_THRESHOLD = 0.7
|
||||
|
||||
@function_tool
|
||||
def query_qdrant(query: str) -> str:
|
||||
"""Retrieve semantically relevant content from Qdrant.
|
||||
|
||||
Args:
|
||||
query: The query to search.
|
||||
"""
|
||||
embedded_query = openai_client.embeddings.create(
|
||||
input=query,
|
||||
model=EMBEDDING_MODEL,
|
||||
).data[0].embedding
|
||||
|
||||
results = qdrant.query_points(
|
||||
collection_name=COLLECTION_NAME,
|
||||
query=embedded_query,
|
||||
limit=LIMIT,
|
||||
score_threshold=SCORE_THRESHOLD,
|
||||
).points
|
||||
|
||||
if results:
|
||||
return "\n".join([point.payload["text"] for point in results])
|
||||
else:
|
||||
return "No results found."
|
||||
|
||||
qdrant_agent = Agent(
|
||||
name="Qdrant searcher",
|
||||
handoff_description="Specialist agent for retrieving info from a Qdrant collection",
|
||||
instructions="You help find answers for user queries using Qdrant. Do not make up any info on your own.",
|
||||
tools=[query_qdrant],
|
||||
)
|
||||
```
|
||||
|
||||
Our `qdrant_agent` can now query a Qdrant collection whenever deemed necessary to answer a user query.
|
||||
|
||||
## Further Reading
|
||||
|
||||
- [Agents Documentation](https://openai.github.io/openai-agents-python/)
|
||||
- [Agents Examples](https://github.com/openai/openai-agents-python/tree/main/examples)
|
||||
@@ -1,171 +0,0 @@
|
||||
---
|
||||
title: OpenAI Swarm
|
||||
---
|
||||
|
||||
# Swarm
|
||||
|
||||
[OpenAI Swarm](https://github.com/openai/swarm) is a Python framework for managing multiple AI agents that can work together. Instead of relying on a single LLM instance to perform all tasks, Swarm allows you to build specialized agents that communicate and collaborate, like a team of experts with unique skills.
|
||||
|
||||
## Getting Started
|
||||
|
||||
To start using Swarm, follow these steps:
|
||||
|
||||
- Install Swarm
|
||||
|
||||
```bash
|
||||
pip install git+https://github.com/openai/swarm.git
|
||||
```
|
||||
|
||||
- Set up your OpenAI API key
|
||||
|
||||
```bash
|
||||
export OPENAI_API_KEY="<YOUR_KEY>"
|
||||
```
|
||||
|
||||
## How Swarm Works
|
||||
|
||||
In Swarm, agents represent individual team members with specific roles and instructions. Each agent can execute tasks or hand off the conversation to another agent, depending on the situation.
|
||||
|
||||
An `Agent` instance simply encapsulates a set of instructions with a set of functions, and has the capability to hand off execution to another Agent.
|
||||
|
||||
These simple building blocks allow you to create complex workflows with a simple mental model.
|
||||
|
||||
## Creating Your First Agents
|
||||
|
||||
Here’s a basic example of two agents:
|
||||
|
||||
- **Agent A**: A helpful assistant.
|
||||
- **Agent B**: An arithmetric specialist.
|
||||
|
||||
Agent A transfers the conversation to Agent B when requested.
|
||||
|
||||
```python
|
||||
from swarm import Swarm, Agent
|
||||
|
||||
client = Swarm()
|
||||
|
||||
# Define Agent B
|
||||
agent_b = Agent(
|
||||
name="Agent B",
|
||||
instructions="Arithmetic solving expertise holder.",
|
||||
)
|
||||
|
||||
def transfer_to_agent_b():
|
||||
return agent_b
|
||||
|
||||
# Define Agent A
|
||||
agent_a = Agent(
|
||||
name="Agent A",
|
||||
instructions="You are a helpful agent.",
|
||||
functions=[transfer_to_agent_b],
|
||||
)
|
||||
|
||||
# Run the interaction
|
||||
response = client.run(
|
||||
agent=agent_a,
|
||||
messages=[{"role": "user", "content": "I want some help with numbers."}],
|
||||
)
|
||||
print(response)
|
||||
```
|
||||
|
||||
In this example, Agent A passes the conversation to Agent B when deemed necessary.
|
||||
|
||||
## Features of an agent
|
||||
|
||||
### 1. **Instructions**
|
||||
|
||||
Agent instructions define their behavior. These are translated into system prompts for conversations. Only the active agent's instructions are used during an interaction.
|
||||
|
||||
### 2. **Functions**
|
||||
|
||||
Agents can execute Python functions, enabling them to perform tasks like processing data or querying databases. Swarm automatically converts functions into a JSON Schema that is passed into Chat Completions tools.
|
||||
|
||||
Example:
|
||||
|
||||
```python
|
||||
def greet(context_variables, language):
|
||||
user_name = context_variables["user_name"]
|
||||
greeting = "Hola" if language.lower() == "spanish" else "Hello"
|
||||
print(f"{greeting}, {user_name}!")
|
||||
return "Done"
|
||||
|
||||
agent = Agent(
|
||||
name="Greeter Agent",
|
||||
functions=[greet],
|
||||
)
|
||||
|
||||
client.run(
|
||||
agent=agent,
|
||||
messages=[{"role": "user", "content": "Greet me in Spanish."}],
|
||||
context_variables={"user_name": "John"},
|
||||
)
|
||||
```
|
||||
|
||||
Errors are handled gracefully by appending an error response to the conversation.
|
||||
|
||||
### 3. **Handoffs**
|
||||
|
||||
If a function returns another agent, the system transfers control to that agent.
|
||||
|
||||
## Integrating Swarm with Qdrant
|
||||
|
||||
You can connect you Swarm agents to retrieve or ingest data into a Qdrant collection. Thereby building you knowledge base. Here’s how to enable an agent to retrieve information from Qdrant.
|
||||
|
||||
Assume you have a Qdrant [collection created](https://qdrant.tech/documentation/concepts/collections/#create-a-collection) using the `"text-embedding-3-small"` model. The payload structure includes a `text` field for knowledge storage.
|
||||
|
||||
```python
|
||||
import qdrant_client
|
||||
from openai import OpenAI
|
||||
|
||||
# Initialize clients
|
||||
openai_client = OpenAI()
|
||||
qdrant = qdrant_client.QdrantClient(host="localhost")
|
||||
|
||||
# Configuration
|
||||
EMBEDDING_MODEL = "text-embedding-3-small"
|
||||
COLLECTION_NAME = "help_center"
|
||||
LIMIT = 5
|
||||
SCORE_THRESHOLD = 0.7
|
||||
|
||||
# Function to query Qdrant
|
||||
def query_qdrant(query):
|
||||
"""Retrieve semantically relevant content from Qdrant."""
|
||||
embedded_query = openai_client.embeddings.create(
|
||||
input=query,
|
||||
model=EMBEDDING_MODEL,
|
||||
).data[0].embedding
|
||||
|
||||
results = qdrant.query_points(
|
||||
collection_name=COLLECTION_NAME,
|
||||
query=embedded_query,
|
||||
limit=LIMIT,
|
||||
score_threshold=SCORE_THRESHOLD,
|
||||
).points
|
||||
|
||||
if results:
|
||||
return {"response": "\n".join([point.payload["text"] for point in results])}
|
||||
else:
|
||||
return {"response": "No results found."}
|
||||
|
||||
# Define agents
|
||||
qdrant_agent = Agent(
|
||||
name="Qdrant Agent",
|
||||
instructions="Retrieve relevant info from a knowledge base stored in Qdrant.",
|
||||
functions=[query_qdrant],
|
||||
)
|
||||
|
||||
def transfer_to_qdrant():
|
||||
return qdrant_agent
|
||||
|
||||
main_agent = Agent(
|
||||
name="Main Agent",
|
||||
instructions="Handle user queries and delegate searches to Qdrant.",
|
||||
functions=[transfer_to_qdrant],
|
||||
)
|
||||
```
|
||||
|
||||
Our `qdrant_agent` can now query a Qdrant collection whenever deemed necessary to answer a user query.
|
||||
|
||||
## Further Reading
|
||||
|
||||
You can find more usage examples in the [Swarm repo](https://github.com/openai/swarm/blob/main/examples/) that further describe its capabilities.
|
||||
Reference in New Issue
Block a user