diff --git a/idea.md b/idea.md deleted file mode 100644 index b237372..0000000 --- a/idea.md +++ /dev/null @@ -1,65 +0,0 @@ - -**Video Title:** -Run LLMs Directly in VS Code with Continue (Alternatives to Cline!) - -**Video Structure & Script Ideas:** - -* **You:** "Hey everyone, I'm going to introduce 'Continue,' a VS Code plugin that solves a common problem with other popular solutions like Cline, and lets you run LLMs locally, directly within your coding environment." - -* **You:** "Lots of people are using plugins like Cline to bring LLMs into VS Code. It’s a great concept! However, Cline has a significant issue: the context window. Cline sends your prompts and code to a remote server, and the size of that context window – the amount of text the LLM can consider – can be *huge*. " - -* **You:** "This means running Cline often requires a powerful GPU. People with older gpu like me, find themselves forced to use smaller, less capable LLMs, like the 0.5B model, just to get it to work." - -* **You:** "That’s where 'Continue' comes in. 'Continue' tackles this problem head-on by using Ollama to run the LLM *locally* on your machine." -* **You:** "This means you can leverage powerful LLMs without needing a cloud connection or a high-end GPU." (Emphasize the key benefit: local, powerful LLMs.) -* **You:** "Critically, Continue's interface lives *inside* VS Code. No more switching back and forth between your editor and a browser window. It's a seamless, integrated experience." -* **Briefly explain Ollama's role:** "Ollama makes running LLMs locally incredibly easy. You don't need to be an AI expert to get started." - -**4. Demo (2:30 - 5:00): Show, Don't Just Tell!** - -* **(Visual: Screen recording of you using "Continue" in VS Code.)** -* **You (Narrating):** - * "Let's walk through a quick example. I have this file open..." (Show the file in VS Code.) - * "To use Continue, I just right-click, and select 'Continue Chat'." (Show the context menu.) - * “You can type in a prompt, like 'Explain this code snippet' and press enter.” (Type a simple prompt and wait for the response.) - * **Show the response appearing directly within VS Code.** - * **Show how you can easily select a block of code and send it to the LLM for analysis or explanation.** "The real power here is the ability to easily select code and send it to the LLM." - * **Show how easy it is to experiment with different LLMs through Ollama.** (If time allows - demonstrates flexibility). - * **Keep it concise and focused on the core benefits (seamless integration, local LLMs).** - -**5. Wrap Up & Call to Action (5:00 - 5:30)** - -* **(Visual: End screen with links and social media handles.)** -* **You:** "So, if you're looking for a way to bring the power of LLMs into your VS Code workflow without the limitations of Cline, 'Continue' is definitely worth checking out.” -* **You:** "I'm going to put a link to the plugin in the description below. Go give it a try and let me know what you think in the comments!" -* **Encourage engagement:** "If you found this video helpful, please like and subscribe for more developer tools and tutorials!" - -**Production Tips:** - -* **Screen Recording Software:** OBS Studio (free), Camtasia (paid). -* **Microphone:** A decent USB microphone will significantly improve audio quality. -* **Lighting:** Good lighting makes you look more professional. -* **Edit!:** Cut out any unnecessary pauses or mistakes. Tight editing makes a big difference. -* **Music:** Background music can add atmosphere, but keep it subtle and non-distracting. Use royalty-free music. - - - -**IMPORTANT CONSIDERATIONS (Read This!)** - -* **Target Audience:** This video is for developers who are already familiar with VS Code and potentially have some interest in using LLMs. Don’t assume *everyone* knows what an LLM is. -* **SEO (Search Engine Optimization):** - * **Keywords:** "VS Code", "LLM", "AI", "Local LLM", "Continue", "Cline", "Ollama" - use these naturally throughout your video title, description, and tags. - * **Thumbnail:** Create a visually appealing thumbnail that clearly communicates the video's topic. Include the "Continue" plugin icon and some text (e.g., "Local LLMs in VS Code"). - * **Description:** Write a detailed description that includes keywords and a summary of the video's content. -* **Engagement is Key:** Respond to comments and questions. Building a community around your channel is crucial for growth. -* **Call to Action Placement:** Put the call to action (subscribe, like) in multiple places: at the beginning, middle, and end of the video. -* **Monetization:** Consider how you might monetize your channel (ads, sponsorships) once you have a decent amount of views. - - - - -To help me refine this further, can you tell me: - -* What level of developer are you targeting? (Beginner, Intermediate, Advanced?) -* Do you want to include a section on how to install Ollama? (It adds complexity, but might be helpful.) -* Are there any specific features of "Continue" that you want to highlight? \ No newline at end of file diff --git a/ollama37/README.md b/ollama37/README.md index 57e8cf5..24f27bf 100644 --- a/ollama37/README.md +++ b/ollama37/README.md @@ -42,6 +42,63 @@ docker run --runtime=nvidia --gpus all -p 11434:11434 dogkeeper886/ollama37 This command will start Ollama and expose it on port `11434`, allowing you to interact with the service. +## Ollama37 Docker Compose + +This `docker-compose.yml` file sets up an Ollama 3.7 container for a more streamlined and persistent environment. It utilizes volumes to persist data and ensures the container automatically restarts if it fails. + +### Prerequisites + +* Docker +* Docker Compose + +### Usage + +1. **Save the `docker-compose.yml` file:** Save the content provided below into a file named `docker-compose.yml` in a convenient directory. + +2. **Run the container:** Open a terminal in the directory where you saved the file and run the following command: + + ```bash + docker-compose up -d + ``` + + This command downloads the `dogkeeper886/ollama37` image (if not already present) and starts the Ollama container in detached mode. + + ```yml + version: '3.8' + + services: + ollama: + image: dogkeeper886/ollama37 + container_name: ollama37 + ports: + - "11434:11434" + volumes: + - ./.ollama:/root/.ollama # Persist Ollama data + restart: unless-stopped # Automatically restart the container + runtime: nvidia # Utilize NVIDIA GPU runtime + ``` + + **Explanation of key `docker-compose.yml` directives:** + + * `version: '3.8'`: Specifies the Docker Compose file version. + * `services.ollama.image: dogkeeper886/ollama37`: Defines the Docker image to use. + * `ports: - "11434:11434"`: Maps port 11434 on the host machine to port 11434 inside the container, making Ollama accessible. + * `volumes: - ./.ollama:/root/.ollama`: **Important:** This mounts a directory named `.ollama` in the same directory as the `docker-compose.yml` file to the `/root/.ollama` directory inside the container. This ensures that downloaded models and Ollama configuration data are persisted even if the container is stopped or removed. Create a `.ollama` directory if it does not already exist. + * `restart: unless-stopped`: This ensures the container automatically restarts if it crashes or is stopped (but not if you explicitly stop it with `docker-compose down`). + * `runtime: nvidia`: Explicitly instructs Docker to use the NVIDIA runtime, ensuring GPU acceleration. + +3. **Accessing Ollama:** After running the container, you can interact with Ollama using its API. Refer to the Ollama documentation for usage details. + +### Stopping the Container + +To stop the container, run: + +```bash +docker-compose down +``` + +This will stop and remove the container, but the data stored in the `.ollama` directory will be preserved. + ## 📦 Version History ### v1.2.0 (2025-05-06) diff --git a/ollama37/docker-compose.yml b/ollama37/docker-compose.yml index 9872914..1cc90cf 100644 --- a/ollama37/docker-compose.yml +++ b/ollama37/docker-compose.yml @@ -7,7 +7,7 @@ services: ports: - "11434:11434" volumes: - - /home/jack/.ollama:/root/.ollama + - ./.ollama:/root/.ollama restart: unless-stopped runtime: nvidia #volumes: