-
Notifications
You must be signed in to change notification settings - Fork 58
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Why text-davinci-003? #1
Comments
I actually had a version with chat api 3.5 turbo, but I didn't like how it
was returning the tasks and executing them.
…On Fri, Apr 14, 2023 at 5:46 PM Sebastian Vates ***@***.***> wrote:
Hi,
first, thx for sharing this neat plugin.
I noticed that the text-davinci-003 model is currently being used for the
agents in this project. However, I am curious about the decision behind
this choice, especially since the gpt-3.5-turbo model is more
cost-effective and allows for defining the AI's role separately.
Based on your experience, is the davinci model more effective in
completing tasks? I would be interested in hearing your thoughts on this
topic.
Thank you,
Sebastian
—
Reply to this email directly, view it on GitHub
<#1>, or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AAJQPTAQLN5RV4P4KKXRJ4DXBHAR5ANCNFSM6AAAAAAW657DEU>
.
You are receiving this because you are subscribed to this thread.Message
ID: ***@***.***>
--
_________________________
*Pietro Schirano*
Senior Product Designer | Brex <http://brex.com>
|
from typing import Dict, List app = Quart(name) Set API KeysOPENAI_API_KEY = "" class BabyAGI: def init(self,
def set_objective(self, objective): def add_task(self, task: Dict): def get_ada_embedding(self, text): def task_creation_agent(self, objective: str, result: str,
async def execution_agent(self, objective: str, task: str) -> str:
async def context_agent(self, query: str, index: str, n: int):
async def search_internet(self, query, api_key, custom_search_engine_id): def clear_task_list(self): baby_agi = BabyAGI(OPENAI_API_KEY, @app.route("/set_objective", methods=["POST"]) @app.route("/add_task", methods=["POST"]) @app.route("/execute_next_task", methods=["POST"]) task = baby_agi.task_list.popleft() new_tasks = baby_agi.task_creation_agent( response = { return jsonify(response) @app.route("/get_task_list", methods=["GET"]) @app.route("/openapi.yaml", methods=["GET"]) @app.route("/logo.png", methods=["GET"]) @app.route("/.well-known/ai-plugin.json", methods=["GET"]) @app.route("/test_google_api", methods=["GET"]) if name == "main": |
Thx for the reply and sharing the code! |
Hi,
first, thx for sharing this neat plugin.
I noticed that the text-davinci-003 model is currently being used for the agents in this project. However, I am curious about the decision behind this choice, especially since the gpt-3.5-turbo model is more cost-effective and allows for defining the AI's role separately.
Based on your experience, is the davinci model more effective in completing tasks? I would be interested in hearing your thoughts on this topic.
Thank you,
Sebastian
The text was updated successfully, but these errors were encountered: