You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+28-7Lines changed: 28 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -40,7 +40,7 @@ Let's assume we want to download utility bills:
40
40
41
41
## Setup
42
42
43
-
1. Set up your OpenAI [API Keys](https://platform.openai.com/account/api-keys) and add the `OPENAI_API_KEY` environment variable. (We recommend your open ai account to have models that are at least as capable as OpenAI o1-mini. Models on par with OpenAI o1-preview are ideal.)
43
+
1. Set up your OpenAI [API Keys](https://platform.openai.com/account/api-keys) and add the `OPENAI_API_KEY` environment variable. (We recommend using an account with access to models that are at least as capable as OpenAI o1-mini. Models on par with OpenAI o1-preview are ideal.)
44
44
2. Install Python requirements via poetry:
45
45
```
46
46
poetry install
@@ -49,14 +49,18 @@ Let's assume we want to download utility bills:
49
49
```
50
50
poetry shell
51
51
```
52
-
4. Run the following command to spawn a browser:
52
+
4. Register the Poetry virtual environment with Jupyter:
53
+
```
54
+
poetry run ipython kernel install --user --name=integuru
55
+
```
56
+
5. Run the following command to spawn a browser:
53
57
```
54
58
poetry run python create_har.py
55
59
```
56
60
Log into your platform and perform the desired action (such as downloading a utility bill).
poetry run integuru --prompt "download utility bills" --model gpt-4o
60
64
```
61
65
You can also run it via Jupyter Notebook `main.ipynb`
62
66
@@ -67,8 +71,8 @@ Let's assume we want to download utility bills:
67
71
After setting up the project, you can use Integuru to analyze and reverse-engineer API requests for external platforms. Simply provide the appropriate .har file and a prompt describing the action that you want to trigger.
68
72
69
73
```
70
-
poetry run python -m integuru --help
71
-
Usage: python -m integuru [OPTIONS]
74
+
poetry run integuru --help
75
+
Usage: integuru [OPTIONS]
72
76
73
77
Options:
74
78
--model TEXT The LLM model to use (default is gpt-4o)
@@ -85,6 +89,7 @@ Options:
85
89
--help Show this message and exit.
86
90
```
87
91
92
+
88
93
## Running Unit Tests
89
94
90
95
To run unit tests using `pytest`, use the following command:
@@ -102,9 +107,14 @@ This repository includes a CI workflow using GitHub Actions. The workflow is def
102
107
3. Installs dependencies using `poetry`.
103
108
4. Runs tests using `pytest`.
104
109
110
+
## Note on 2FA
111
+
112
+
When the destination site uses two-factor authentication (2FA), the workflow remains the same. Ensure that you complete the 2FA process and obtain the cookies/auth tokens/session tokens after 2FA. These tokens will be used in the workflow.
@@ -115,3 +125,14 @@ Contributions to improve Integuru are welcome. Please feel free to submit issues
115
125
Integuru is built by Integuru.ai. Besides our work on the agent, we take custom requests for new integrations or additional features for existing supported platforms. We also offer hosting and authentication services. If you have requests or want to work with us, reach out at [email protected].
116
126
117
127
We open-source unofficial APIs that we've built already. You can find them [here](https://github.com/Integuru-AI/APIs-by-Integuru).
128
+
129
+
## Privacy Policy
130
+
131
+
### Data Storage
132
+
Collected data is stored locally in the `network_requests.har` and `cookies.json` files.
133
+
134
+
### LLM Usage
135
+
The tool uses a cloud-based LLM (OpenAI's GPT-4o and o1-preview models).
136
+
137
+
### LLM Training
138
+
The LLM is not trained or improved by the usage of this tool.
0 commit comments