modified the env
This commit is contained in:
Gormery Kombo Wanjiru
@@ -1,44 +1,44 @@
|
||||
{
|
||||
"name": "ollama-docker",
|
||||
"dockerComposeFile": ["../docker-compose.yml"],
|
||||
"service": "app",
|
||||
"workspaceFolder": "/code",
|
||||
"customizations": {
|
||||
"vscode": {
|
||||
"extensions": [
|
||||
"ms-python.python",
|
||||
"ms-python.vscode-pylance",
|
||||
"ms-python.autopep8",
|
||||
"ms-python.debugpy",
|
||||
"ms-python.isort",
|
||||
"donjayamanne.python-environment-manager",
|
||||
"donjayamanne.python-extension-pack",
|
||||
"etmoffat.pip-packages",
|
||||
"aaron-bond.better-comments",
|
||||
"formulahendry.auto-rename-tag",
|
||||
"formulahendry.code-runner",
|
||||
"github.copilot",
|
||||
"github.vscode-pull-request-github",
|
||||
"ms-azuretools.vscode-docker",
|
||||
"ms-vscode-remote.remote-containers",
|
||||
"ms-vscode-remote.remote-ssh",
|
||||
"ms-vscode-remote.vscode-remote-extensionpack",
|
||||
"ms-toolsai.jupyter",
|
||||
"ritwickdey.liveserver",
|
||||
"visualstudioexptteam.vscodeintellicode",
|
||||
"vscode-icons-team.vscode-icons",
|
||||
"esbenp.prettier-vscode",
|
||||
"jpotterm.simple-vim"
|
||||
],
|
||||
"settings": {
|
||||
"python.pythonPath": "/usr/local/bin/python",
|
||||
"python.linting.pylintEnabled": false,
|
||||
"python.linting.flake8Enabled": true,
|
||||
"python.linting.flake8Args": ["--max-line-length=88"],
|
||||
"python.formatting.provider": "ms-python.python",
|
||||
"editor.formatOnSave": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"postCreateCommand": "pip install -r requirements.txt"
|
||||
}
|
||||
{
|
||||
"name": "ollama-docker",
|
||||
"dockerComposeFile": ["../docker-compose.yml"],
|
||||
"service": "app",
|
||||
"workspaceFolder": "/code",
|
||||
"customizations": {
|
||||
"vscode": {
|
||||
"extensions": [
|
||||
"ms-python.python",
|
||||
"ms-python.vscode-pylance",
|
||||
"ms-python.autopep8",
|
||||
"ms-python.debugpy",
|
||||
"ms-python.isort",
|
||||
"donjayamanne.python-environment-manager",
|
||||
"donjayamanne.python-extension-pack",
|
||||
"etmoffat.pip-packages",
|
||||
"aaron-bond.better-comments",
|
||||
"formulahendry.auto-rename-tag",
|
||||
"formulahendry.code-runner",
|
||||
"github.copilot",
|
||||
"github.vscode-pull-request-github",
|
||||
"ms-azuretools.vscode-docker",
|
||||
"ms-vscode-remote.remote-containers",
|
||||
"ms-vscode-remote.remote-ssh",
|
||||
"ms-vscode-remote.vscode-remote-extensionpack",
|
||||
"ms-toolsai.jupyter",
|
||||
"ritwickdey.liveserver",
|
||||
"visualstudioexptteam.vscodeintellicode",
|
||||
"vscode-icons-team.vscode-icons",
|
||||
"esbenp.prettier-vscode",
|
||||
"jpotterm.simple-vim"
|
||||
],
|
||||
"settings": {
|
||||
"python.pythonPath": "/usr/local/bin/python",
|
||||
"python.linting.pylintEnabled": false,
|
||||
"python.linting.flake8Enabled": true,
|
||||
"python.linting.flake8Args": ["--max-line-length=88"],
|
||||
"python.formatting.provider": "ms-python.python",
|
||||
"editor.formatOnSave": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"postCreateCommand": "pip install -r requirements.txt"
|
||||
}
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
# flyctl launch added from .gitignore
|
||||
**\.dist
|
||||
**\.vscode
|
||||
src\__pycache__
|
||||
fly.toml
|
||||
# flyctl launch added from .gitignore
|
||||
**\.dist
|
||||
**\.vscode
|
||||
src\__pycache__
|
||||
fly.toml
|
||||
|
||||
6
.gitignore
vendored
6
.gitignore
vendored
@@ -1,4 +1,4 @@
|
||||
.dist
|
||||
/src/__pycache__
|
||||
venv/
|
||||
.dist
|
||||
/src/__pycache__
|
||||
venv/
|
||||
ollama/
|
||||
54
.vscode/extensions.json
vendored
54
.vscode/extensions.json
vendored
@@ -1,28 +1,28 @@
|
||||
{
|
||||
"recommendations": [
|
||||
"ms-python.python",
|
||||
"ms-python.vscode-pylance",
|
||||
"ms-python.autopep8",
|
||||
"ms-python.debugpy",
|
||||
"ms-python.isort",
|
||||
"donjayamanne.python-environment-manager",
|
||||
"donjayamanne.python-extension-pack",
|
||||
"etmoffat.pip-packages",
|
||||
"aaron-bond.better-comments",
|
||||
"formulahendry.auto-rename-tag",
|
||||
"formulahendry.code-runner",
|
||||
"github.copilot",
|
||||
"github.vscode-pull-request-github",
|
||||
"ms-azuretools.vscode-docker",
|
||||
"ms-vscode-remote.remote-containers",
|
||||
"ms-vscode-remote.remote-ssh",
|
||||
"ms-vscode-remote.vscode-remote-extensionpack",
|
||||
"ms-toolsai.jupyter",
|
||||
"ritwickdey.liveserver",
|
||||
"visualstudioexptteam.vscodeintellicode",
|
||||
"vscode-icons-team.vscode-icons",
|
||||
"esbenp.prettier-vscode"
|
||||
]
|
||||
}
|
||||
|
||||
{
|
||||
"recommendations": [
|
||||
"ms-python.python",
|
||||
"ms-python.vscode-pylance",
|
||||
"ms-python.autopep8",
|
||||
"ms-python.debugpy",
|
||||
"ms-python.isort",
|
||||
"donjayamanne.python-environment-manager",
|
||||
"donjayamanne.python-extension-pack",
|
||||
"etmoffat.pip-packages",
|
||||
"aaron-bond.better-comments",
|
||||
"formulahendry.auto-rename-tag",
|
||||
"formulahendry.code-runner",
|
||||
"github.copilot",
|
||||
"github.vscode-pull-request-github",
|
||||
"ms-azuretools.vscode-docker",
|
||||
"ms-vscode-remote.remote-containers",
|
||||
"ms-vscode-remote.remote-ssh",
|
||||
"ms-vscode-remote.vscode-remote-extensionpack",
|
||||
"ms-toolsai.jupyter",
|
||||
"ritwickdey.liveserver",
|
||||
"visualstudioexptteam.vscodeintellicode",
|
||||
"vscode-icons-team.vscode-icons",
|
||||
"esbenp.prettier-vscode"
|
||||
]
|
||||
}
|
||||
|
||||
|
||||
8
.vscode/settings.json
vendored
8
.vscode/settings.json
vendored
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"python.languageServer": "Pylance",
|
||||
"python.analysis.extraPaths": ["../"],
|
||||
"python.formatting.provider": "prettier",
|
||||
{
|
||||
"python.languageServer": "Pylance",
|
||||
"python.analysis.extraPaths": ["../"],
|
||||
"python.formatting.provider": "prettier",
|
||||
}
|
||||
30
Dockerfile
30
Dockerfile
@@ -1,13 +1,17 @@
|
||||
FROM python:3.11-slim
|
||||
|
||||
WORKDIR /code
|
||||
|
||||
COPY ./requirements.txt ./
|
||||
|
||||
RUN pip install --no-cache-dir -r requirements.txt
|
||||
|
||||
COPY ./src ./src
|
||||
|
||||
EXPOSE 8000
|
||||
|
||||
CMD ["uvicorn", "src.main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]
|
||||
FROM python:3.11-slim
|
||||
|
||||
WORKDIR /code
|
||||
|
||||
COPY ./requirements.txt ./
|
||||
|
||||
RUN apt-get update && apt-get install git -y && apt-get install curl -y
|
||||
|
||||
RUN curl -fsSL https://ollama.com/install.sh | sh
|
||||
|
||||
RUN pip install --no-cache-dir -r requirements.txt
|
||||
|
||||
COPY ./src ./src
|
||||
|
||||
EXPOSE 8000
|
||||
|
||||
CMD ["uvicorn", "src.main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]
|
||||
|
||||
190
README.md
190
README.md
@@ -1,96 +1,96 @@
|
||||
# Ollama Docker Compose Setup
|
||||
|
||||
Welcome to the Ollama Docker Compose Setup! This project simplifies the deployment of Ollama using Docker Compose, making it easy to run Ollama with all its dependencies in a containerized environment.
|
||||
|
||||
## Getting Started
|
||||
|
||||
### Prerequisites
|
||||
|
||||
Make sure you have the following prerequisites installed on your machine:
|
||||
|
||||
- Docker
|
||||
- Docker Compose
|
||||
|
||||
#### GPU Support (Optional)
|
||||
|
||||
If you have a GPU and want to leverage its power within a Docker container, follow these steps to install the NVIDIA Container Toolkit:
|
||||
|
||||
```bash
|
||||
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
|
||||
&& curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
|
||||
sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
|
||||
sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y nvidia-container-toolkit
|
||||
|
||||
# Configure NVIDIA Container Toolkit
|
||||
sudo nvidia-ctk runtime configure --runtime=docker
|
||||
sudo systemctl restart docker
|
||||
|
||||
# Test GPU integration
|
||||
docker run --gpus all nvidia/cuda:11.5.2-base-ubuntu20.04 nvidia-smi
|
||||
```
|
||||
|
||||
### Configuration
|
||||
|
||||
1. Clone the Docker Compose repository:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/valiantlynx/ollama-docker.git
|
||||
```
|
||||
|
||||
2. Change to the project directory:
|
||||
|
||||
```bash
|
||||
cd ollama-docker
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
Start Ollama and its dependencies using Docker Compose:
|
||||
|
||||
if gpu is configured
|
||||
```bash
|
||||
docker-compose -f docker-compose-ollama-gpu.yaml up -d
|
||||
```
|
||||
|
||||
else
|
||||
```bash
|
||||
docker-compose up -d
|
||||
```
|
||||
|
||||
Visit [http://localhost:3000](http://localhost:3000) in your browser to access Ollama-webui.
|
||||
|
||||
### Model Installation
|
||||
|
||||
Navigate to settings -> model and install a model (e.g., llama2). This may take a couple of minutes, but afterward, you can use it just like ChatGPT.
|
||||
|
||||
### Explore Langchain and Ollama
|
||||
|
||||
You can explore Langchain and Ollama within the project. A third container named **app** has been created for this purpose. Inside, you'll find some examples.
|
||||
|
||||
### Devcontainer and Virtual Environment
|
||||
|
||||
The **app** container serves as a devcontainer, allowing you to boot into it for experimentation. Additionally, the run.sh file contains code to set up a virtual environment if you prefer not to use Docker for your development environment.
|
||||
|
||||
## Stop and Cleanup
|
||||
|
||||
To stop the containers and remove the network:
|
||||
|
||||
```bash
|
||||
docker-compose down
|
||||
```
|
||||
|
||||
## Contributing
|
||||
|
||||
We welcome contributions! If you'd like to contribute to the Ollama Docker Compose Setup, please follow our [Contribution Guidelines](CONTRIBUTING.md).
|
||||
|
||||
## License
|
||||
|
||||
This project is licensed under the [MIT License](LICENSE). Feel free to use, modify, and distribute it according to the terms of the license. Just give me a mention and some credit
|
||||
|
||||
## Contact
|
||||
|
||||
If you have any questions or concerns, please contact us at [vantlynxz@gmail.com](mailto:vantlynxz@gmail.com).
|
||||
|
||||
# Ollama Docker Compose Setup
|
||||
|
||||
Welcome to the Ollama Docker Compose Setup! This project simplifies the deployment of Ollama using Docker Compose, making it easy to run Ollama with all its dependencies in a containerized environment.
|
||||
|
||||
## Getting Started
|
||||
|
||||
### Prerequisites
|
||||
|
||||
Make sure you have the following prerequisites installed on your machine:
|
||||
|
||||
- Docker
|
||||
- Docker Compose
|
||||
|
||||
#### GPU Support (Optional)
|
||||
|
||||
If you have a GPU and want to leverage its power within a Docker container, follow these steps to install the NVIDIA Container Toolkit:
|
||||
|
||||
```bash
|
||||
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
|
||||
&& curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
|
||||
sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
|
||||
sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y nvidia-container-toolkit
|
||||
|
||||
# Configure NVIDIA Container Toolkit
|
||||
sudo nvidia-ctk runtime configure --runtime=docker
|
||||
sudo systemctl restart docker
|
||||
|
||||
# Test GPU integration
|
||||
docker run --gpus all nvidia/cuda:11.5.2-base-ubuntu20.04 nvidia-smi
|
||||
```
|
||||
|
||||
### Configuration
|
||||
|
||||
1. Clone the Docker Compose repository:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/valiantlynx/ollama-docker.git
|
||||
```
|
||||
|
||||
2. Change to the project directory:
|
||||
|
||||
```bash
|
||||
cd ollama-docker
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
Start Ollama and its dependencies using Docker Compose:
|
||||
|
||||
if gpu is configured
|
||||
```bash
|
||||
docker-compose -f docker-compose-ollama-gpu.yaml up -d
|
||||
```
|
||||
|
||||
else
|
||||
```bash
|
||||
docker-compose up -d
|
||||
```
|
||||
|
||||
Visit [http://localhost:3000](http://localhost:3000) in your browser to access Ollama-webui.
|
||||
|
||||
### Model Installation
|
||||
|
||||
Navigate to settings -> model and install a model (e.g., llama2). This may take a couple of minutes, but afterward, you can use it just like ChatGPT.
|
||||
|
||||
### Explore Langchain and Ollama
|
||||
|
||||
You can explore Langchain and Ollama within the project. A third container named **app** has been created for this purpose. Inside, you'll find some examples.
|
||||
|
||||
### Devcontainer and Virtual Environment
|
||||
|
||||
The **app** container serves as a devcontainer, allowing you to boot into it for experimentation. Additionally, the run.sh file contains code to set up a virtual environment if you prefer not to use Docker for your development environment.
|
||||
|
||||
## Stop and Cleanup
|
||||
|
||||
To stop the containers and remove the network:
|
||||
|
||||
```bash
|
||||
docker-compose down
|
||||
```
|
||||
|
||||
## Contributing
|
||||
|
||||
We welcome contributions! If you'd like to contribute to the Ollama Docker Compose Setup, please follow our [Contribution Guidelines](CONTRIBUTING.md).
|
||||
|
||||
## License
|
||||
|
||||
This project is licensed under the [MIT License](LICENSE). Feel free to use, modify, and distribute it according to the terms of the license. Just give me a mention and some credit
|
||||
|
||||
## Contact
|
||||
|
||||
If you have any questions or concerns, please contact us at [vantlynxz@gmail.com](mailto:vantlynxz@gmail.com).
|
||||
|
||||
Enjoy using Ollama with Docker Compose! 🐳🚀
|
||||
@@ -1,35 +1,35 @@
|
||||
version: '3.8'
|
||||
|
||||
services:
|
||||
ollama:
|
||||
volumes:
|
||||
- ./ollama/ollama:/root/.ollama
|
||||
container_name: ollama
|
||||
pull_policy: always
|
||||
tty: true
|
||||
restart: unless-stopped
|
||||
image: ollama/ollama:latest
|
||||
ports:
|
||||
- 11434:11434
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
devices:
|
||||
- driver: nvidia
|
||||
count: 1
|
||||
capabilities: [gpu]
|
||||
|
||||
ollama-webui:
|
||||
image: ghcr.io/ollama-webui/ollama-webui:main
|
||||
container_name: ollama-webui
|
||||
volumes:
|
||||
- ./ollama/ollama-webui:/app/backend/data
|
||||
depends_on:
|
||||
- ollama
|
||||
ports:
|
||||
- 3000:8080
|
||||
environment:
|
||||
- '/ollama/api=http://ollama:11434/api'
|
||||
extra_hosts:
|
||||
- host.docker.internal:host-gateway
|
||||
version: '3.8'
|
||||
|
||||
services:
|
||||
ollama:
|
||||
volumes:
|
||||
- ./ollama/ollama:/root/.ollama
|
||||
container_name: ollama
|
||||
pull_policy: always
|
||||
tty: true
|
||||
restart: unless-stopped
|
||||
image: ollama/ollama:latest
|
||||
ports:
|
||||
- 11434:11434
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
devices:
|
||||
- driver: nvidia
|
||||
count: 1
|
||||
capabilities: [gpu]
|
||||
|
||||
ollama-webui:
|
||||
image: ghcr.io/ollama-webui/ollama-webui:main
|
||||
container_name: ollama-webui
|
||||
volumes:
|
||||
- ./ollama/ollama-webui:/app/backend/data
|
||||
depends_on:
|
||||
- ollama
|
||||
ports:
|
||||
- 3000:8080
|
||||
environment:
|
||||
- '/ollama/api=http://ollama:11434/api'
|
||||
extra_hosts:
|
||||
- host.docker.internal:host-gateway
|
||||
restart: unless-stopped
|
||||
@@ -1,52 +1,52 @@
|
||||
version: '3.8'
|
||||
services:
|
||||
app:
|
||||
build: .
|
||||
ports:
|
||||
- 8000:8000
|
||||
- 5678:5678
|
||||
volumes:
|
||||
- .:/code
|
||||
command: uvicorn src.main:app --host 0.0.0.0 --port 8000 --reload
|
||||
restart: always
|
||||
depends_on:
|
||||
- ollama
|
||||
- llama-webui
|
||||
networks:
|
||||
- ollama-docker
|
||||
|
||||
ollama:
|
||||
image: ollama/ollama:latest
|
||||
ports:
|
||||
- 11434:11434
|
||||
volumes:
|
||||
- .:/code
|
||||
- ./ollama/ollama:/root/.ollama
|
||||
container_name: ollama
|
||||
pull_policy: always
|
||||
tty: true
|
||||
restart: always
|
||||
networks:
|
||||
- ollama-docker
|
||||
|
||||
llama-webui:
|
||||
image: ghcr.io/ollama-webui/ollama-webui:main
|
||||
container_name: ollama-webui
|
||||
volumes:
|
||||
- ./ollama/ollama-webui:/app/backend/data
|
||||
depends_on:
|
||||
- ollama
|
||||
ports:
|
||||
- 3000:8080
|
||||
environment:
|
||||
- '/ollama/api=http://ollama:11434/api'
|
||||
extra_hosts:
|
||||
- host.docker.internal:host-gateway
|
||||
restart: unless-stopped
|
||||
networks:
|
||||
- ollama-docker
|
||||
|
||||
networks:
|
||||
ollama-docker:
|
||||
external: false
|
||||
|
||||
version: '3.8'
|
||||
services:
|
||||
app:
|
||||
build: .
|
||||
ports:
|
||||
- 8000:8000
|
||||
- 5678:5678
|
||||
volumes:
|
||||
- .:/code
|
||||
command: uvicorn src.main:app --host 0.0.0.0 --port 8000 --reload
|
||||
restart: always
|
||||
depends_on:
|
||||
- ollama
|
||||
- llama-webui
|
||||
networks:
|
||||
- ollama-docker
|
||||
|
||||
ollama:
|
||||
image: ollama/ollama:latest
|
||||
ports:
|
||||
- 11434:11434
|
||||
volumes:
|
||||
- .:/code
|
||||
- ./ollama/ollama:/root/.ollama
|
||||
container_name: ollama
|
||||
pull_policy: always
|
||||
tty: true
|
||||
restart: always
|
||||
networks:
|
||||
- ollama-docker
|
||||
|
||||
llama-webui:
|
||||
image: ghcr.io/ollama-webui/ollama-webui:main
|
||||
container_name: ollama-webui
|
||||
volumes:
|
||||
- ./ollama/ollama-webui:/app/backend/data
|
||||
depends_on:
|
||||
- ollama
|
||||
ports:
|
||||
- 3000:8080
|
||||
environment:
|
||||
- '/ollama/api=http://ollama:11434/api'
|
||||
extra_hosts:
|
||||
- host.docker.internal:host-gateway
|
||||
restart: unless-stopped
|
||||
networks:
|
||||
- ollama-docker
|
||||
|
||||
networks:
|
||||
ollama-docker:
|
||||
external: false
|
||||
|
||||
|
||||
34
fly.toml
34
fly.toml
@@ -1,17 +1,17 @@
|
||||
# fly.toml app configuration file generated for breath-first-search on 2023-10-17T03:52:02+02:00
|
||||
#
|
||||
# See https://fly.io/docs/reference/configuration/ for information about how to use this file.
|
||||
#
|
||||
|
||||
app = "ollama-docker"
|
||||
primary_region = "arn"
|
||||
|
||||
[env]
|
||||
PORT = "8000"
|
||||
|
||||
[http_service]
|
||||
internal_port = 8000
|
||||
force_https = true
|
||||
auto_stop_machines = true
|
||||
auto_start_machines = true
|
||||
min_machines_running = 0
|
||||
# fly.toml app configuration file generated for breath-first-search on 2023-10-17T03:52:02+02:00
|
||||
#
|
||||
# See https://fly.io/docs/reference/configuration/ for information about how to use this file.
|
||||
#
|
||||
|
||||
app = "ollama-docker"
|
||||
primary_region = "arn"
|
||||
|
||||
[env]
|
||||
PORT = "8000"
|
||||
|
||||
[http_service]
|
||||
internal_port = 8000
|
||||
force_https = true
|
||||
auto_stop_machines = true
|
||||
auto_start_machines = true
|
||||
min_machines_running = 0
|
||||
|
||||
12
model_file
12
model_file
@@ -1,6 +1,6 @@
|
||||
FROM llama2
|
||||
|
||||
PARAMETER temperature 0.8
|
||||
|
||||
SYSTEM You are a financial assistant, you help classify expenses
|
||||
and income from bank transactions
|
||||
FROM llama2
|
||||
|
||||
PARAMETER temperature 0.8
|
||||
|
||||
SYSTEM You are a financial assistant, you help classify expenses
|
||||
and income from bank transactions
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
fastapi
|
||||
uvicorn
|
||||
debugpy
|
||||
langchain-community
|
||||
langchain
|
||||
langchainhub
|
||||
gpt4all
|
||||
chromadb
|
||||
requests
|
||||
fastapi
|
||||
uvicorn
|
||||
debugpy
|
||||
langchain-community
|
||||
langchain
|
||||
langchainhub
|
||||
gpt4all
|
||||
chromadb
|
||||
requests
|
||||
beautifulsoup4
|
||||
14
run.bat
14
run.bat
@@ -1,7 +1,7 @@
|
||||
call python -m venv venv
|
||||
call venv\Scripts\activate
|
||||
|
||||
call python -m pip install --upgrade pip
|
||||
|
||||
call pip install -r requirements.txt
|
||||
call python signal-processing.py
|
||||
call python -m venv venv
|
||||
call venv\Scripts\activate
|
||||
|
||||
call python -m pip install --upgrade pip
|
||||
|
||||
call pip install -r requirements.txt
|
||||
call python signal-processing.py
|
||||
|
||||
10
run.sh
10
run.sh
@@ -1,5 +1,5 @@
|
||||
python -m venv venv
|
||||
source venv/Scripts/activate
|
||||
pip install -r requirements.txt
|
||||
python src/test.py
|
||||
|
||||
python -m venv venv
|
||||
source venv/Scripts/activate
|
||||
pip install -r requirements.txt
|
||||
python src/test.py
|
||||
|
||||
|
||||
16
setup.sh
16
setup.sh
@@ -1,8 +1,8 @@
|
||||
# run using docker
|
||||
docker build -t ollama-docker-image .
|
||||
docker run --name ollama-docker-container -d -p 11434:11434 -p 8000:8000 -v $(pwd):/code ollama-docker-image
|
||||
|
||||
#connect to turborepo
|
||||
git subtree add --prefix=apps/ollama-docker https://github.com/valiantlynx/ollama-docker.git main --squash
|
||||
git subtree pull --prefix=apps/ollama-docker https://github.com/valiantlynx/ollama-docker.git main --squash
|
||||
git subtree push --prefix=apps/ollama-docker https://github.com/valiantlynx/ollama-docker.git main
|
||||
# run using docker
|
||||
docker build -t ollama-docker-image .
|
||||
docker run --name ollama-docker-container -d -p 11434:11434 -p 8000:8000 -v $(pwd):/code ollama-docker-image
|
||||
|
||||
#connect to turborepo
|
||||
git subtree add --prefix=apps/ollama-docker https://github.com/valiantlynx/ollama-docker.git main --squash
|
||||
git subtree pull --prefix=apps/ollama-docker https://github.com/valiantlynx/ollama-docker.git main --squash
|
||||
git subtree push --prefix=apps/ollama-docker https://github.com/valiantlynx/ollama-docker.git main
|
||||
|
||||
@@ -1,23 +1,23 @@
|
||||
from langchain.llms import Ollama
|
||||
from langchain.callbacks.manager import CallbackManager
|
||||
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
|
||||
|
||||
llm = Ollama(model="llama2-uncensored",
|
||||
# callback_manager = CallbackManager([StreamingStdOutCallbackHandler()]),
|
||||
temperature=0.9,
|
||||
)
|
||||
|
||||
from langchain.prompts import PromptTemplate
|
||||
|
||||
prompt = PromptTemplate(
|
||||
input_variables=["topic"],
|
||||
template="Give me 5 interesting facts about {topic}?",
|
||||
)
|
||||
|
||||
from langchain.chains import LLMChain
|
||||
chain = LLMChain(llm=llm,
|
||||
prompt=prompt,
|
||||
verbose=False)
|
||||
|
||||
# Run the chain only specifying the input variable.
|
||||
print(chain.run("the moon"))
|
||||
from langchain.llms import Ollama
|
||||
from langchain.callbacks.manager import CallbackManager
|
||||
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
|
||||
|
||||
llm = Ollama(model="llama2-uncensored",
|
||||
# callback_manager = CallbackManager([StreamingStdOutCallbackHandler()]),
|
||||
temperature=0.9,
|
||||
)
|
||||
|
||||
from langchain.prompts import PromptTemplate
|
||||
|
||||
prompt = PromptTemplate(
|
||||
input_variables=["topic"],
|
||||
template="Give me 5 interesting facts about {topic}?",
|
||||
)
|
||||
|
||||
from langchain.chains import LLMChain
|
||||
chain = LLMChain(llm=llm,
|
||||
prompt=prompt,
|
||||
verbose=False)
|
||||
|
||||
# Run the chain only specifying the input variable.
|
||||
print(chain.run("the moon"))
|
||||
|
||||
246
src/index.html
246
src/index.html
@@ -1,123 +1,123 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<link href="https://cdn.jsdelivr.net/npm/daisyui@3.7.3/dist/full.css" rel="stylesheet" type="text/css">
|
||||
<script src="https://cdn.tailwindcss.com"></script>
|
||||
<script src="https://unpkg.com/htmx.org"></script>
|
||||
<script src="https://unpkg.com/htmx.org/dist/ext/client-side-templates.js"></script>
|
||||
<script src="https://cdn.jsdelivr.net/npm/nunjucks@3.2.4/browser/nunjucks.min.js"></script>
|
||||
<script>
|
||||
// CORS workaround
|
||||
document.addEventListener("htmx:configRequest", (evt) => {
|
||||
evt.detail.headers = [];
|
||||
});
|
||||
</script>
|
||||
<title>Whisper Magic Chat</title>
|
||||
</head>
|
||||
|
||||
<body class="bg-gradient-to-r from-blue-600 via-purple-600 to-pink-600 font-sans">
|
||||
|
||||
<header class="bg-opacity-90 backdrop-filter backdrop-blur-lg py-6">
|
||||
<div class="container mx-auto flex justify-between items-center">
|
||||
<h1 class="text-3xl md:text-4xl lg:text-5xl font-extrabold text-white">Whisper Magic Chat</h1>
|
||||
<nav>
|
||||
<ul class="flex space-x-4">
|
||||
<li><a href="/" class="hover:text-gray-300 text-white">Home</a></li>
|
||||
<li><a href="#features" class="hover:text-gray-300 text-white">Features</a></li>
|
||||
<li><a href="/docs" class="hover:text-gray-300 text-white">Docs</a></li>
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
</header>
|
||||
|
||||
<section id="hero" class="bg-gray-900 text-white py-16">
|
||||
<div class="container mx-auto text-center">
|
||||
<h2 class="text-4xl lg:text-5xl font-semibold mb-4">Unleash the Magic of Your Voice</h2>
|
||||
<p class="text-lg lg:text-xl text-gray-300 leading-7 mb-8">Transform your voice into something enchanting with
|
||||
Whisper Magic API. Experience the future of automatic speech recognition with unparalleled accuracy and speed.</p>
|
||||
<a href="#transcribe"
|
||||
class="bg-blue-500 text-white px-8 py-3 rounded-full hover:bg-blue-700 transition duration-300">Get
|
||||
Started</a>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section id="transcribe" class="bg-gray-100 py-16" hx-ext="client-side-templates">
|
||||
<div class="container mx-auto text-center">
|
||||
<h2 class="text-3xl lg:text-4xl font-semibold mb-6 text-gray-800">Whisper Magic Transcription</h2>
|
||||
<p class="text-lg lg:text-xl text-gray-700 mb-6">Upload an audio file to transcribe and experience the magic of
|
||||
Whisper.</p>
|
||||
|
||||
<form hx-post="/transcribe" hx-trigger="submit" hx-swap="outerHTML" enctype="multipart/form-data"
|
||||
class="flex flex-col items-center space-y-4" nunjucks-template="chat" _='on htmx:xhr:progress(loaded, total) set #progress.value to (loaded/total)*100'>
|
||||
<input type="file" name="files" class="p-4 border border-gray-300 rounded">
|
||||
<button type="submit"
|
||||
class="bg-blue-500 text-white px-8 py-3 rounded-full hover:bg-blue-700 transition duration-300">Transcribe</button>
|
||||
<progress id='progress' value='0' max='100' class="w-full h-4 bg-blue-200 rounded-full"></progress>
|
||||
<!-- HTMX and Nunjucks templates -->
|
||||
<template id="chat">
|
||||
<!-- totalItems -->
|
||||
{% if results == 1 %}
|
||||
<i class="text-gray-500 mb-4"> Found {{ results.length }} files.</i>
|
||||
{% endif %}
|
||||
<!-- items -->
|
||||
{% for chat in results %}
|
||||
<div class="block mb-8 mx-auto max-w-md bg-white rounded-lg p-4 shadow-md hover:shadow-lg">
|
||||
<div class="flex items-center">
|
||||
<div class="w-10 h-10 rounded-full overflow-hidden mr-4">
|
||||
<img alt="Whisper Magic transcription icon"
|
||||
src="https://api.dicebear.com/7.x/adventurer/svg?seed={{ chat.filename }}"
|
||||
class="object-cover w-full h-full">
|
||||
</div>
|
||||
<div>
|
||||
<span class="text-blue-500 font-bold">Whisper:</span>
|
||||
<time class="text-xs opacity-50 block">{{ chat.filename | truncate(10, true, "")}}</time>
|
||||
</div>
|
||||
</div>
|
||||
<div class="mt-4">{{ chat.transcript }}</div>
|
||||
<div class="mt-4 text-blue-500 hover:underline">
|
||||
<a href="javascript:location.reload(true);" rel="noopener noreferrer">Retry?</a>
|
||||
</div>
|
||||
</div>
|
||||
{% endfor %}
|
||||
</template>
|
||||
</form>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section id="features" class="bg-gray-800 text-white py-16">
|
||||
<div class="container mx-auto text-center">
|
||||
<h2 class="text-3xl lg:text-4xl font-semibold mb-12">Enchanting Features</h2>
|
||||
<div class="grid grid-cols-1 md:grid-cols-3 gap-8">
|
||||
<!-- Feature 1 -->
|
||||
<div class="p-8 bg-white bg-opacity-70 rounded-lg shadow-md">
|
||||
<h3 class="text-2xl font-semibold mb-4 text-gray-800">Voice Transformation</h3>
|
||||
<p class="text-gray-700">Turn your voice into a symphony of magical sounds. Choose from a variety of
|
||||
enchanting transformations.</p>
|
||||
</div>
|
||||
<!-- Feature 2 -->
|
||||
<div class="p-8 bg-white bg-opacity-70 rounded-lg shadow-md">
|
||||
<h3 class="text-2xl font-semibold mb-4 text-gray-800">Whisper Recognition</h3>
|
||||
<p class="text-gray-700">Whisper Magic recognizes whispers with unparalleled precision, making it perfect for
|
||||
ASMR applications.</p>
|
||||
</div>
|
||||
<!-- Feature 3 -->
|
||||
<div class="p-8 bg-white bg-opacity-70 rounded-lg shadow-md">
|
||||
<h3 class="text-2xl font-semibold mb-4 text-gray-800">Real-time Spell Casting</h3>
|
||||
<p class="text-gray-700">Cast spells using your voice in real-time. Experience the magic as your words come to
|
||||
life.</p>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<footer class="bg-gray-900 text-white py-6">
|
||||
<div class="container mx-auto text-center">
|
||||
<p>© 2024 Whisper Magic. All Rights Reserved.</p>
|
||||
</div>
|
||||
</footer>
|
||||
</body>
|
||||
|
||||
</html>
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<link href="https://cdn.jsdelivr.net/npm/daisyui@3.7.3/dist/full.css" rel="stylesheet" type="text/css">
|
||||
<script src="https://cdn.tailwindcss.com"></script>
|
||||
<script src="https://unpkg.com/htmx.org"></script>
|
||||
<script src="https://unpkg.com/htmx.org/dist/ext/client-side-templates.js"></script>
|
||||
<script src="https://cdn.jsdelivr.net/npm/nunjucks@3.2.4/browser/nunjucks.min.js"></script>
|
||||
<script>
|
||||
// CORS workaround
|
||||
document.addEventListener("htmx:configRequest", (evt) => {
|
||||
evt.detail.headers = [];
|
||||
});
|
||||
</script>
|
||||
<title>Whisper Magic Chat</title>
|
||||
</head>
|
||||
|
||||
<body class="bg-gradient-to-r from-blue-600 via-purple-600 to-pink-600 font-sans">
|
||||
|
||||
<header class="bg-opacity-90 backdrop-filter backdrop-blur-lg py-6">
|
||||
<div class="container mx-auto flex justify-between items-center">
|
||||
<h1 class="text-3xl md:text-4xl lg:text-5xl font-extrabold text-white">Whisper Magic Chat</h1>
|
||||
<nav>
|
||||
<ul class="flex space-x-4">
|
||||
<li><a href="/" class="hover:text-gray-300 text-white">Home</a></li>
|
||||
<li><a href="#features" class="hover:text-gray-300 text-white">Features</a></li>
|
||||
<li><a href="/docs" class="hover:text-gray-300 text-white">Docs</a></li>
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
</header>
|
||||
|
||||
<section id="hero" class="bg-gray-900 text-white py-16">
|
||||
<div class="container mx-auto text-center">
|
||||
<h2 class="text-4xl lg:text-5xl font-semibold mb-4">Unleash the Magic of Your Voice</h2>
|
||||
<p class="text-lg lg:text-xl text-gray-300 leading-7 mb-8">Transform your voice into something enchanting with
|
||||
Whisper Magic API. Experience the future of automatic speech recognition with unparalleled accuracy and speed.</p>
|
||||
<a href="#transcribe"
|
||||
class="bg-blue-500 text-white px-8 py-3 rounded-full hover:bg-blue-700 transition duration-300">Get
|
||||
Started</a>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section id="transcribe" class="bg-gray-100 py-16" hx-ext="client-side-templates">
|
||||
<div class="container mx-auto text-center">
|
||||
<h2 class="text-3xl lg:text-4xl font-semibold mb-6 text-gray-800">Whisper Magic Transcription</h2>
|
||||
<p class="text-lg lg:text-xl text-gray-700 mb-6">Upload an audio file to transcribe and experience the magic of
|
||||
Whisper.</p>
|
||||
|
||||
<form hx-post="/transcribe" hx-trigger="submit" hx-swap="outerHTML" enctype="multipart/form-data"
|
||||
class="flex flex-col items-center space-y-4" nunjucks-template="chat" _='on htmx:xhr:progress(loaded, total) set #progress.value to (loaded/total)*100'>
|
||||
<input type="file" name="files" class="p-4 border border-gray-300 rounded">
|
||||
<button type="submit"
|
||||
class="bg-blue-500 text-white px-8 py-3 rounded-full hover:bg-blue-700 transition duration-300">Transcribe</button>
|
||||
<progress id='progress' value='0' max='100' class="w-full h-4 bg-blue-200 rounded-full"></progress>
|
||||
<!-- HTMX and Nunjucks templates -->
|
||||
<template id="chat">
|
||||
<!-- totalItems -->
|
||||
{% if results == 1 %}
|
||||
<i class="text-gray-500 mb-4"> Found {{ results.length }} files.</i>
|
||||
{% endif %}
|
||||
<!-- items -->
|
||||
{% for chat in results %}
|
||||
<div class="block mb-8 mx-auto max-w-md bg-white rounded-lg p-4 shadow-md hover:shadow-lg">
|
||||
<div class="flex items-center">
|
||||
<div class="w-10 h-10 rounded-full overflow-hidden mr-4">
|
||||
<img alt="Whisper Magic transcription icon"
|
||||
src="https://api.dicebear.com/7.x/adventurer/svg?seed={{ chat.filename }}"
|
||||
class="object-cover w-full h-full">
|
||||
</div>
|
||||
<div>
|
||||
<span class="text-blue-500 font-bold">Whisper:</span>
|
||||
<time class="text-xs opacity-50 block">{{ chat.filename | truncate(10, true, "")}}</time>
|
||||
</div>
|
||||
</div>
|
||||
<div class="mt-4">{{ chat.transcript }}</div>
|
||||
<div class="mt-4 text-blue-500 hover:underline">
|
||||
<a href="javascript:location.reload(true);" rel="noopener noreferrer">Retry?</a>
|
||||
</div>
|
||||
</div>
|
||||
{% endfor %}
|
||||
</template>
|
||||
</form>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section id="features" class="bg-gray-800 text-white py-16">
|
||||
<div class="container mx-auto text-center">
|
||||
<h2 class="text-3xl lg:text-4xl font-semibold mb-12">Enchanting Features</h2>
|
||||
<div class="grid grid-cols-1 md:grid-cols-3 gap-8">
|
||||
<!-- Feature 1 -->
|
||||
<div class="p-8 bg-white bg-opacity-70 rounded-lg shadow-md">
|
||||
<h3 class="text-2xl font-semibold mb-4 text-gray-800">Voice Transformation</h3>
|
||||
<p class="text-gray-700">Turn your voice into a symphony of magical sounds. Choose from a variety of
|
||||
enchanting transformations.</p>
|
||||
</div>
|
||||
<!-- Feature 2 -->
|
||||
<div class="p-8 bg-white bg-opacity-70 rounded-lg shadow-md">
|
||||
<h3 class="text-2xl font-semibold mb-4 text-gray-800">Whisper Recognition</h3>
|
||||
<p class="text-gray-700">Whisper Magic recognizes whispers with unparalleled precision, making it perfect for
|
||||
ASMR applications.</p>
|
||||
</div>
|
||||
<!-- Feature 3 -->
|
||||
<div class="p-8 bg-white bg-opacity-70 rounded-lg shadow-md">
|
||||
<h3 class="text-2xl font-semibold mb-4 text-gray-800">Real-time Spell Casting</h3>
|
||||
<p class="text-gray-700">Cast spells using your voice in real-time. Experience the magic as your words come to
|
||||
life.</p>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<footer class="bg-gray-900 text-white py-6">
|
||||
<div class="container mx-auto text-center">
|
||||
<p>© 2024 Whisper Magic. All Rights Reserved.</p>
|
||||
</div>
|
||||
</footer>
|
||||
</body>
|
||||
|
||||
</html>
|
||||
|
||||
54
src/main.py
54
src/main.py
@@ -1,28 +1,28 @@
|
||||
from fastapi import FastAPI
|
||||
from fastapi.responses import HTMLResponse
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
import debugpy
|
||||
from typing import List
|
||||
|
||||
|
||||
app = FastAPI()
|
||||
# Allow all origins for CORS (you can customize this based on your requirements)
|
||||
origins = ["*"]
|
||||
|
||||
# Configure CORS middleware
|
||||
app.add_middleware(
|
||||
CORSMiddleware,
|
||||
allow_origins=origins,
|
||||
allow_credentials=True,
|
||||
allow_methods=["*"],
|
||||
allow_headers=["*"],
|
||||
)
|
||||
debugpy.listen(("0.0.0.0", 5678))
|
||||
|
||||
@app.get("/", response_class=HTMLResponse)
|
||||
async def read_root():
|
||||
# Read the content of your HTML file
|
||||
with open("./src/index.html", "r") as file:
|
||||
html_content = file.read()
|
||||
|
||||
from fastapi import FastAPI
|
||||
from fastapi.responses import HTMLResponse
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
import debugpy
|
||||
from typing import List
|
||||
|
||||
|
||||
app = FastAPI()
|
||||
# Allow all origins for CORS (you can customize this based on your requirements)
|
||||
origins = ["*"]
|
||||
|
||||
# Configure CORS middleware
|
||||
app.add_middleware(
|
||||
CORSMiddleware,
|
||||
allow_origins=origins,
|
||||
allow_credentials=True,
|
||||
allow_methods=["*"],
|
||||
allow_headers=["*"],
|
||||
)
|
||||
debugpy.listen(("0.0.0.0", 5678))
|
||||
|
||||
@app.get("/", response_class=HTMLResponse)
|
||||
async def read_root():
|
||||
# Read the content of your HTML file
|
||||
with open("./src/index.html", "r") as file:
|
||||
html_content = file.read()
|
||||
|
||||
return HTMLResponse(content=html_content)
|
||||
140
src/rag.py
140
src/rag.py
@@ -1,71 +1,71 @@
|
||||
# Load web page
|
||||
import argparse
|
||||
|
||||
from langchain.document_loaders import WebBaseLoader
|
||||
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
||||
|
||||
# Embed and store
|
||||
from langchain.vectorstores import Chroma
|
||||
from langchain.embeddings import GPT4AllEmbeddings
|
||||
from langchain.embeddings import OllamaEmbeddings # We can also try Ollama embeddings
|
||||
|
||||
from langchain.llms import Ollama
|
||||
from langchain.callbacks.manager import CallbackManager
|
||||
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description='Filter out URL argument.')
|
||||
parser.add_argument('--url', type=str, default='https://valiantlynx.com', required=True, help='The URL to filter out.')
|
||||
|
||||
args = parser.parse_args()
|
||||
url = args.url
|
||||
print(f"using URL: {url}")
|
||||
|
||||
loader = WebBaseLoader(url)
|
||||
data = loader.load()
|
||||
|
||||
# Split into chunks
|
||||
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1500, chunk_overlap=100)
|
||||
all_splits = text_splitter.split_documents(data)
|
||||
print(f"Split into {len(all_splits)} chunks")
|
||||
|
||||
vectorstore = Chroma.from_documents(documents=all_splits,
|
||||
embedding=GPT4AllEmbeddings())
|
||||
|
||||
# Retrieve
|
||||
# question = "What are the latest headlines on {url}?"
|
||||
# docs = vectorstore.similarity_search(question)
|
||||
|
||||
print(f"Loaded {len(data)} documents")
|
||||
# print(f"Retrieved {len(docs)} documents")
|
||||
|
||||
# RAG prompt
|
||||
from langchain import hub
|
||||
QA_CHAIN_PROMPT = hub.pull("rlm/rag-prompt-llama")
|
||||
|
||||
|
||||
# LLM
|
||||
llm = Ollama(model="llama2-uncensored",
|
||||
verbose=True,
|
||||
callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]))
|
||||
print(f"Loaded LLM model {llm.model}")
|
||||
|
||||
# QA chain
|
||||
from langchain.chains import RetrievalQA
|
||||
qa_chain = RetrievalQA.from_chain_type(
|
||||
llm,
|
||||
retriever=vectorstore.as_retriever(),
|
||||
chain_type_kwargs={"prompt": QA_CHAIN_PROMPT},
|
||||
|
||||
)
|
||||
|
||||
# Ask a question
|
||||
question = f"summarize what this blog is trying to say? {url}?"
|
||||
result = qa_chain({"query": question})
|
||||
|
||||
# print(result)
|
||||
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# Load web page
|
||||
import argparse
|
||||
|
||||
from langchain.document_loaders import WebBaseLoader
|
||||
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
||||
|
||||
# Embed and store
|
||||
from langchain.vectorstores import Chroma
|
||||
from langchain.embeddings import GPT4AllEmbeddings
|
||||
from langchain.embeddings import OllamaEmbeddings # We can also try Ollama embeddings
|
||||
|
||||
from langchain.llms import Ollama
|
||||
from langchain.callbacks.manager import CallbackManager
|
||||
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description='Filter out URL argument.')
|
||||
parser.add_argument('--url', type=str, default='https://valiantlynx.com', required=True, help='The URL to filter out.')
|
||||
|
||||
args = parser.parse_args()
|
||||
url = args.url
|
||||
print(f"using URL: {url}")
|
||||
|
||||
loader = WebBaseLoader(url)
|
||||
data = loader.load()
|
||||
|
||||
# Split into chunks
|
||||
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1500, chunk_overlap=100)
|
||||
all_splits = text_splitter.split_documents(data)
|
||||
print(f"Split into {len(all_splits)} chunks")
|
||||
|
||||
vectorstore = Chroma.from_documents(documents=all_splits,
|
||||
embedding=GPT4AllEmbeddings())
|
||||
|
||||
# Retrieve
|
||||
# question = "What are the latest headlines on {url}?"
|
||||
# docs = vectorstore.similarity_search(question)
|
||||
|
||||
print(f"Loaded {len(data)} documents")
|
||||
# print(f"Retrieved {len(docs)} documents")
|
||||
|
||||
# RAG prompt
|
||||
from langchain import hub
|
||||
QA_CHAIN_PROMPT = hub.pull("rlm/rag-prompt-llama")
|
||||
|
||||
|
||||
# LLM
|
||||
llm = Ollama(model="llama2-uncensored",
|
||||
verbose=True,
|
||||
callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]))
|
||||
print(f"Loaded LLM model {llm.model}")
|
||||
|
||||
# QA chain
|
||||
from langchain.chains import RetrievalQA
|
||||
qa_chain = RetrievalQA.from_chain_type(
|
||||
llm,
|
||||
retriever=vectorstore.as_retriever(),
|
||||
chain_type_kwargs={"prompt": QA_CHAIN_PROMPT},
|
||||
|
||||
)
|
||||
|
||||
# Ask a question
|
||||
question = f"summarize what this blog is trying to say? {url}?"
|
||||
result = qa_chain({"query": question})
|
||||
|
||||
# print(result)
|
||||
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
18
src/test.py
18
src/test.py
@@ -1,10 +1,10 @@
|
||||
from langchain.llms import Ollama
|
||||
from langchain.callbacks.manager import CallbackManager
|
||||
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
|
||||
|
||||
llm = Ollama(
|
||||
base_url="http://localhost:11434",
|
||||
model="llama2-uncensored",
|
||||
callback_manager = CallbackManager([StreamingStdOutCallbackHandler()]))
|
||||
|
||||
from langchain.llms import Ollama
|
||||
from langchain.callbacks.manager import CallbackManager
|
||||
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
|
||||
|
||||
llm = Ollama(
|
||||
base_url="http://localhost:11434",
|
||||
model="llama2-uncensored",
|
||||
callback_manager = CallbackManager([StreamingStdOutCallbackHandler()]))
|
||||
|
||||
llm("hello:")
|
||||
Reference in New Issue
Block a user