Skip to content

Commit dc035f7

Browse files
📝 Complete doc (#36)
1 parent 095fb0c commit dc035f7

File tree

2 files changed

+52
-48
lines changed

2 files changed

+52
-48
lines changed

README.md

Lines changed: 52 additions & 48 deletions
Original file line numberDiff line numberDiff line change
@@ -1,82 +1,86 @@
11
# 🤖 Agent Z transcribe podcast
2+
23
<!-- ALL-CONTRIBUTORS-BADGE:START - Do not remove or modify this section -->
34
[![All Contributors](https://img.shields.io/badge/all_contributors-4-orange.svg?style=flat-square)](#contributors)
45
<!-- ALL-CONTRIBUTORS-BADGE:END -->
6+
[![Release](https://github.com/zenika-open-source/agent-Z-transcribe-podcast/actions/workflows/release.yml/badge.svg)](https://github.com/zenika-open-source/agent-Z-transcribe-podcast/actions/workflows/release.yml)
7+
[![GitHub Release](https://img.shields.io/github/v/release/zenika-open-source/agent-Z-transcribe-podcast)](https://github.com/zenika-open-source/agent-Z-transcribe-podcast/releases)
8+
9+
This is an AI Agent to transcribe podcasts to be easily readable as a book 🤘
10+
11+
## ✨ Features
512

6-
This is an IA Agent to transcribe podcasts to be easily readable as a book 🤘
13+
- **Podcast Transcription**: Transcribes French tech podcasts into readable text.
14+
- **Timestamps**: Option to include timestamps in the transcription.
15+
- **Download**: Save transcription as a Markdown file directly from the browser (compatible with Cloud Run).
16+
- **Modern AI**: Powered by Gemini 1.5 Pro.
17+
18+
![Agent Z Transcribe](./docs/screen.png)
719

820
## 🛠️ Configuration
921

22+
**Prerequisites:**
23+
- Java 25
24+
1025
1️⃣ Export these 2 variables:
1126
```sh
1227
export GOOGLE_GENAI_USE_VERTEXAI=FALSE
1328
export GOOGLE_API_KEY=<your gemini API>
1429
```
1530

16-
2️⃣ Create a `.env file`. The template `.env-template` in avaiable.
31+
2️⃣ Create a `.env` file. The template `.env-template` is available.
1732

18-
## Development
33+
## 🧑‍💻 Development
1934

2035
To run your agent (if you have only one specific agent):
2136

2237
```sh
2338
mvn dependency:build-classpath -Dmdep.outputFile=cp.txt && java -cp target/classes:$(cat cp.txt) transcribe.ZPodcastTranscribe
2439
```
2540

26-
To run the UI, run this command and go to ```http://localhost:8888```
27-
28-
![Agent Z Transcribe](docs/screen.png)
41+
Then go to [http://localhost:8080/](http://localhost:8080/).
2942

3043
## 🐳 Docker
3144

32-
This app could be runned with Docker and this command
33-
```
34-
docker build -t agent-z-transcribe-podcast
35-
docker run -p 8888:8888 -e PORT=8888 agent-z-transcribe-podcast
36-
```
37-
38-
## 🚀 Deployment
39-
40-
To deploy on Cloud Run:
41-
42-
- authentification on GCP with `gcloud auth login`
43-
44-
- configure settings exporting variables:
45-
46-
```sh
47-
export GOOGLE_CLOUD_PROJECT=<your projet>
48-
export GOOGLE_CLOUD_LOCATION=<location like europe-west1>
49-
export GOOGLE_GENAI_USE_VERTEXAI=<true if you deploy on Google Cloud, else false>
50-
export GOOGLE_API_KEY=<your GOOGLE API KEY>
51-
```
52-
53-
or adding them into a `.env` file (cf `env-template` file)
54-
```
55-
export GCLOUD_PROJECT=
56-
export GCLOUD_LOCATION=europe-west1
57-
export GCLOUD_GENAI_USE_VERTEXAI=FALSE
58-
export GOOGLE_API_KEY=
59-
```
60-
61-
- and run the `gcloud` command.
45+
This app can be run with Docker:
6246

6347
```sh
64-
gcloud run deploy agent-z-transcribe-podcast \
65-
--source . \
66-
--region $GCLOUD_LOCATION \
67-
--project $GCLOUD_PROJECT \
68-
--allow-unauthenticated \
69-
--memory 1Gi \
70-
--max-instances 1 \
71-
--set-env-vars="GOOGLE_CLOUD_PROJECT=$GCLOUD_PROJECT,GOOGLE_CLOUD_LOCATION=$GCLOUD_LOCATION,GOOGLE_GENAI_USE_VERTEXAI=$GCLOUD_GENAI_USE_VERTEXAI,GOOGLE_API_KEY=$GOOGLE_API_KEY"
72-
48+
docker build -t agent-z-transcribe-podcast .
49+
docker run -p 8080:8080 -e PORT=8080 agent-z-transcribe-podcast
7350
```
7451

52+
## 🚀 Deployment
7553

76-
## ✨Contribute
77-
78-
Anyone can contribute to this project. For the moment, please add your question or purpose something in [a new issue](https://github.com/zenika-open-source/opensource-statistics/issues).
54+
To deploy on Cloud Run:
7955

56+
1. Authenticate on GCP:
57+
```sh
58+
gcloud auth login
59+
```
60+
61+
2. Configure settings by exporting variables:
62+
```sh
63+
export GOOGLE_CLOUD_PROJECT=<your project>
64+
export GOOGLE_CLOUD_LOCATION=<location like europe-west1>
65+
export GOOGLE_GENAI_USE_VERTEXAI=<true if you deploy on Google Cloud, else false>
66+
export GOOGLE_API_KEY=<your GOOGLE API KEY>
67+
```
68+
69+
3. Deploy using `gcloud`:
70+
```sh
71+
gcloud run deploy agent-z-transcribe-podcast \
72+
--source . \
73+
--region $GOOGLE_CLOUD_LOCATION \
74+
--project $GOOGLE_CLOUD_PROJECT \
75+
--allow-unauthenticated \
76+
--memory 1Gi \
77+
--max-instances 1 \
78+
--set-env-vars="GOOGLE_CLOUD_PROJECT=$GOOGLE_CLOUD_PROJECT,GOOGLE_CLOUD_LOCATION=$GOOGLE_CLOUD_LOCATION,GOOGLE_GENAI_USE_VERTEXAI=$GOOGLE_GENAI_USE_VERTEXAI,GOOGLE_API_KEY=$GOOGLE_API_KEY"
79+
```
80+
81+
## ✨ Contribute
82+
83+
Anyone can contribute to this project. For the moment, please add your question or purpose something in [a new issue](https://github.com/zenika-open-source/agent-Z-transcribe-podcast/issues).
8084
8185
## 🙏 Contributors
8286

docs/screen.png

3.92 KB
Loading

0 commit comments

Comments
 (0)