Ollama on Ghafoor's Personal Blog

How to use prompts with OpenManus

noreply@example.com (AG Sayyed) — Thu, 15 May 2025 15:00:53 +0000

OpenManus Usage Guide

Setup

1# Clone (already done)
2cd ~/Documents/projects/uv/OpenManus
3
4# Run from OpenManus directory (recommended)
5cd ~/Documents/projects/uv/OpenManus && uv run main.py --prompt "your task here"

Running from Anywhere

Option 1: Full path (easiest)

1cd ~/Documents/projects/uv/OpenManus && uv run main.py --prompt "your task here"

Option 2: From this folder (HBstack blog)

1uv run ~/Documents/projects/uv/OpenManus/main.py --prompt "your task here"

Option 3: Interactive mode

1cd ~/Documents/projects/uv/OpenManus && uv run main.py
2# Then type your prompt when asked

Option 4: Planning flow (for complex multi-step tasks)

1cd ~/Documents/projects/uv/OpenManus && uv run run_flow.py

Current Config

Setting	Value
Provider	OpenRouter
Model	`anthropic/claude-haiku-4.5`
Input cost	$1.00 per million tokens
Output cost	$5.00 per million tokens
Max steps	20 (per session)

Writing Good Prompts

✅ DO: Be specific with a deliverable

Good Prompt	Why
`Analyze my Hugo site at /home/ag-sayyed/Documents/projects/hbstack/ghafoors-blog and give a summary of the theme, config, and content structure`	Clear goal + output format
`Find all broken internal links in my Hugo site at /path/to/site`	Specific task, measurable result
`Add a new "contact" page with a form to my Hugo site at /path/to/site`	Concrete deliverable
`Update the homepage hero section to say "Welcome to my blog" in /path/to/site`	Small, focused change
`List all custom shortcodes in /path/to/site and explain what each does`	Specific scope
`Suggest 3 performance improvements for my Hugo site based on /path/to/site/config.toml`	Analytical, bounded task

❌ AVOID: Vague prompts with no deliverable

Bad Prompt	Problem
`Explore my Hugo site`	No goal — wanders aimlessly, wastes tokens
`Look at my site`	Same — no clear end condition
`Check my config`	Too vague, doesn’t know what to check for
`Help me with my site`	Way too broad

💡 Tips to Save Money

Be specific about which files — instead of “analyze my site”, say “check config.toml and the homepage content”
Set a clear output — “give me a bullet list”, “write the changes to file X”, “summarize in 3 sentences”
One task at a time — each prompt is a fresh session, so break big jobs into focused steps
Use full paths — always include the absolute path to your project so OpenManus finds it regardless of where you run from

Cost Reference (Haiku 4.5)

Activity	Approx Cost
Listing a directory + reading 2 files	~$0.02
Reading a whole Hugo config + summary	~$0.05
Creating a new page with content	~$0.10
Full site analysis (10+ files)	~$0.30
Complex multi-step task (20 steps)	~$1.00–2.00

Quick Alias (Optional)

Add to ~/.bashrc:

OpenManus

noreply@example.com (AG Sayyed) — Sun, 11 May 2025 15:00:53 +0000

OpenManus for Local LLMs

noreply@example.com (AG Sayyed) — Sun, 11 May 2025 15:00:53 +0000

OpenManus Installation and Usage Guide

OpenManus repository on GitHub.

Install uvicorn for running the FastAPI server.

1$ curl -LsSf https://astral.sh/uv/install.sh | sh
2uv -h
3uv -V

Essential uv Commands

Category	Command	Description
Environments	uv venv	Creates a new virtual environment in the .venv folder.
	source .venv/bin/activate	Activates the environment (macOS/Linux).
	.venv\Scripts\activate	Activates the environment (Windows).
	deactivate	Exits the currently active environment.
Project Management	uv init	Sets up a new project with a pyproject.toml file.
	uv add `<package>`	Adds a dependency and automatically updates the environment.
	uv sync	Synchronises the environment with the lockfile (installs/removes).
	uv run `<script>`	Runs a script without needing to manually activate the env.
Pip Interface	uv pip install -r reqs.txt	Fast alternative to pip install for existing requirement files.
	uv pip tree	Displays a visual tree of all installed dependencies.
Python Versions	uv python list	Shows available Python versions you can install.
	uv python install 3.12	Downloads and installs a specific Python version automatically.

Clone the OpenManus repository and navigate to the project directory.

1git clone https://github.com/FoundationAgents/OpenManus.git
2cd OpenManus

Install the required dependencies using pip.

1uv pip install -r requirements.txt

Configure toml file

OpenManus uses a config.toml file to specify the LLMs and their configurations. You can create this file in the root directory of the project.

OpenWebUI

noreply@example.com (AG Sayyed) — Sun, 11 May 2025 15:00:53 +0000

OpenWebUI transforms how you interact with your local language models, providing a sleek, feature-rich interface that makes working with models like Llama, Mistral, and others both powerful and intuitive.

What is OpenWebUI

OpenWebUI is an open-source, browser-based graphical user interface designed specifically for interacting with local large language models (LLMs), particularly those running through Ollama. It provides a ChatGPT-like experience for your self-hosted AI models, combining the privacy benefits of running local models with the usability of commercial AI platforms.

Hyper Parameters

noreply@example.com (AG Sayyed) — Tue, 11 Feb 2025 18:55:28 +0000

This guide covers the key hyperparameters that influence the performance of AI models, including context window size and embedding size.

Context Windows Size

Context window size is the maximum number of tokens the model can process in a single input. It determines the model’s ability to understand and generate text based on the context provided. If you increase the context window size, the model can consider more information when generating responses, but it may require more memory and processing power. It happens when it has to remember what was asked earlier. In other words, it’s how much of the conversation or input history the model considers when making its predictions. For example, if you’re having a conversation with the AI, the context window determines how many of the previous messages the model can “remember” and use to generate a coherent response. A larger context window means the model can take into account more of the previous conversation, leading to more contextually aware responses, but it can also require more computational resources, which can slow down performance. The context window size keep increasing as the conversation goes on.

AVX Technology Explained

noreply@example.com (AG Sayyed) — Fri, 31 Jan 2025 21:12:40 +0000

AVX Technology Explained

AVX (Advanced Vector Extensions) is a CPU instruction set extension designed for high-performance computing. It was first introduced by Intel in 2011 with the Sandy Bridge processor architecture.

How AVX Works

At its core, AVX allows a single instruction to operate on multiple data points simultaneously, following the SIMD (Single Instruction, Multiple Data) computing paradigm:

Without AVX: Process data one piece at a time
With AVX: Process multiple pieces of data in parallel with a single instruction

AVX Versions

AVX (2011): Original version with 256-bit wide vector operations
AVX2 (2013): Added more instructions and expanded integer operations
AVX-512 (2016+): Further expanded to 512-bit operations

Why AVX2 Matters for AI and Machine Learning

Modern AI frameworks and LLM runtimes require AVX2 because:

Setting Up Text Generation WebUI (No AVX Required)

noreply@example.com (AG Sayyed) — Fri, 31 Jan 2025 21:12:40 +0000

Setting Up Text Generation WebUI (No AVX Required)

Text Generation WebUI is a great alternative to LM Studio that offers non-AVX builds, making it compatible with older CPUs. There are several installation options available:

Option-1 One-Click Installer (Recommended)

Visit the official GitHub repository
Download the installer that specifies “Non-AVX” support:
- For Windows: oobabooga-windows-noavx.zip
- For Linux: oobabooga-linux-noavx.zip
Extract the zip file and run:
- Windows: start_windows.bat
- Linux: start_linux.sh

Option-2 Manual Installation

If you prefer manual installation: