Question 1

How do I deploy my agency to production?

Accepted Answer

Build a dedicated API backend (FastAPI is recommended) that manages authentication and persists thread state using callbacks. See the Deployment to Production guide for detailed steps.

Question 2

How can I serve an Agency as an API using FastAPI?

Accepted Answer

Embed your agency within a FastAPI endpoint: ```python from fastapi import FastAPI from uuid import uuid4 app = FastAPI() @app.post("/chat") async def chat(user_request: UserRequest): chat_id = user_request.chat_id or str(uuid4()) agency = Agency( agent, load_threads_callback=lambda: load_threads(chat_id), save_threads_callback=lambda thread_dict: save_threads(thread_dict, chat_id) ) response = await agency.get_response(user_request.message) return {"chat_id": chat_id, "response": response.final_output} ``` Or use the built‑in FastAPI integration: ```python agency.run_fastapi(host="0.0.0.0", port=8000) ```

Question 3

Why is the CodeInterpreter tool automatically added?

Accepted Answer

When file types like .json, .docx, or .pptx are uploaded, the CodeInterpreter tool is auto‑added to process them. To change this behavior, update the agent’s instructions or create a custom file‑handling tool.

Question 4

How can I transfer data between tools and agents?

Accepted Answer

There are two ways to transfer data between tools and agents: use the agency context inside your tools, or create a tool that uploads files to storage and outputs a file ID. The file ID can then be used by other tools or agents.

Question 5

How do I manage multiple users with Agency Swarm?

Accepted Answer

To support multiple users or chats, you need to load and save thread IDs in your database for each user. Ensure each chat/user has a unique thread ID and follow the Deployment to Production guide for more details.

Question 6

How do I save and continue conversations?

Accepted Answer

To persist conversations between application restarts, implement callbacks that save and load the full message history from a local file. For example, define your callback functions: ```python import os, json def load_threads(chat_id: str) -> list[dict]: """Load all threads data for a specific chat session.""" if os.path.exists(f"{chat_id}_threads.json"): with open(f"{chat_id}_threads.json", "r") as file: return json.load(file) return [] def save_threads(thread_dict: list[dict], chat_id: str): """Save all threads data to file.""" with open(f"{chat_id}_threads.json", "w") as file: json.dump(thread_dict, file) ``` Then pass these callbacks when initializing the agency: ```python from agency_swarm import Agency agency = Agency( agent, load_threads_callback=lambda: load_threads(chat_id), save_threads_callback=lambda thread_dict: save_threads(thread_dict, chat_id), ) ``` This setup preserves your conversation context between runs.

Question 7

Can I use open source models with Agency Swarm?

Accepted Answer

Yes—you can use third‑party models for simple, non‑mission‑critical tasks (usually one or two tools per agent). See the Third‑Party Models documentation for more information. Keep in mind that many third‑party models currently struggle with function calling.

Question 8

How do I set my OpenAI API key in my project?

Accepted Answer

Set your API key in your code: ```python from agency_swarm import set_openai_key set_openai_key("YOUR_API_KEY") ``` Or use a .env file: ``` OPENAI_API_KEY=sk-1234... ``` Then load it with: ```python from dotenv import load_dotenv load_dotenv() ```

Agency SwarmAtvērtā AI ģeneratīvais orķestrācijas ramatnieks, pieejams arī atvērtos avotos, kuru galvenais uzdevums ir automātizēt un samazināt AI reālisma procesu darbību, ar sabiedrisku agentu vājiem.

Pārskats

Galvenās funkcijas

Cenas

Lietošanas gadījumi

Automatizēt AI attīstības darbības protokolu

Būvēt vairākjēdznieka lietojumprogrammas

Atvērti lietojumprogrammu rīki, lai koordinētu uzdevumu dekontesacijas starp rīkiem

Eksperimentējiet ar aģentu sadarbības modeliem

Plusi un mīnusi

Plusi

Mīnusi

Kauju rekords

Last battle

Atsauksmes

Solid for our team

Solid for our team

Compared a few options

Skeptical, then convinced

Years in this space

Jautājumi

Uzdod jautājumu

Rīkīgi izstrādājamas AI Biedrības Frameworks alternatīvas

Pārskats

Galvenās funkcijas

Cenas

Lietošanas gadījumi

Automatizēt AI attīstības darbības protokolu

Būvēt vairākjēdznieka lietojumprogrammas

Atvērti lietojumprogrammu rīki, lai koordinētu uzdevumu dekontesacijas starp rīkiem

Eksperimentējiet ar aģentu sadarbības modeliem

Plusi un mīnusi

Plusi

Mīnusi

Kauju rekords

Last battle

Atsauksmes

Solid for our team

Solid for our team

Compared a few options

Skeptical, then convinced

Years in this space

Jautājumi

Uzdod jautājumu

Rīkīgi izstrādājamas AI Biedrības Frameworks alternatīvas

Trending now