Spaces:
Sleeping
Sleeping
Charles Azam
commited on
Commit
Β·
a0b6cc3
1
Parent(s):
534f864
init: add readme and initialise package
Browse files- .python-version +1 -0
- README.md +51 -2
- pyproject.toml +17 -0
- src/deepengineer/__init__.py +3 -0
.python-version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
3.13
|
README.md
CHANGED
@@ -1,2 +1,51 @@
|
|
1 |
-
#
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# DeepEngineer π¬
|
2 |
+
|
3 |
+
> A deep search agentic system for scientific and engineering workflows
|
4 |
+
|
5 |
+
## π― About
|
6 |
+
|
7 |
+
DeepEngineer is an open-source project designed to build a specialized agentic system that assists engineers and scientists. The ultimate vision is to create an AI agent that can reason, plan, and execute complex tasks, effectively augmenting and accelerating the engineering and scientific workflow.
|
8 |
+
|
9 |
+
### π Vision
|
10 |
+
|
11 |
+
The project is inspired by the outstanding challenge in AI to address the complexities of numerical simulation-intensive science and engineering. As noted in recent research, this requires a sophisticated composition of scientific reasoning with the ability to operate specialized software and tools.
|
12 |
+
|
13 |
+
> *"Addressing the degree of complexity required in numerical simulation-intensive science and engineering workflows β which requires the composition of scientific reasoning with the ability to operate simulation software β remains an outstanding challenge."*
|
14 |
+
> β [FEABench: Evaluating Language Models on Multiphysics
|
15 |
+
Reasoning Ability](https://arxiv.org/abs/2504.06260)
|
16 |
+
|
17 |
+
This project aims to tackle this challenge by creating an agent with the following core capabilities:
|
18 |
+
|
19 |
+
### βοΈ Current objective
|
20 |
+
|
21 |
+
It is likely that this project will not be better than the non specialized deepsearch solutions like OpenAI's or Magnus on scientific questions. Even though those solutions tend to focus on software development, they are generally very good at everything.
|
22 |
+
|
23 |
+
That being said, I hope to learn a lot and I see it as a personal challenge to deploy this solution and then iterate on it. Well see.
|
24 |
+
|
25 |
+
## Getting starded
|
26 |
+
|
27 |
+
## Installation
|
28 |
+
|
29 |
+
```bash
|
30 |
+
git clone https://github.com/your_username_/DeepEngineer.git
|
31 |
+
cd DeepEngineer
|
32 |
+
uv sync
|
33 |
+
```
|
34 |
+
|
35 |
+
### π οΈ Tool Use
|
36 |
+
|
37 |
+
The minimum tools needed are:
|
38 |
+
- Web crawler agent
|
39 |
+
- Scientific paper analyser agent
|
40 |
+
- Drawing agent
|
41 |
+
- Coding Agent
|
42 |
+
|
43 |
+
### Packages used
|
44 |
+
- smolagents
|
45 |
+
- crawl4ai
|
46 |
+
|
47 |
+
### External APIs
|
48 |
+
- Mistral (OCR)
|
49 |
+
- Deepseek (LLM)
|
50 |
+
- Perplexity / Talily / Wikipedia / Arxiv
|
51 |
+
|
pyproject.toml
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[project]
|
2 |
+
name = "deepengineer"
|
3 |
+
version = "0.1.0"
|
4 |
+
description = "DeepEngineer is a deepsearch project focused on engineering"
|
5 |
+
readme = "README.md"
|
6 |
+
authors = [
|
7 |
+
{ name = "Charles Azam", email = "azamcharles0@gmail.com" }
|
8 |
+
]
|
9 |
+
requires-python = ">=3.13"
|
10 |
+
dependencies = []
|
11 |
+
|
12 |
+
[project.scripts]
|
13 |
+
deepengineer = "deepengineer:main"
|
14 |
+
|
15 |
+
[build-system]
|
16 |
+
requires = ["hatchling"]
|
17 |
+
build-backend = "hatchling.build"
|
src/deepengineer/__init__.py
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
def main() -> None:
|
2 |
+
print("Hello from deepengineer!")
|
3 |
+
|