I have tried open web UI and it's great when it works but for some reason it's not super reliable or always fast enough for me.

I'm just wondering if there's any simpler tools or projects to integrate voice mode with Ollama models that people have found it and like. Thanks!

Alpaca (flathub) does not work with Ollama Cloud. It does not work either with local models or with cloud models. He doesn't produce any answers. Does anyone know the problem yet and can tell me more about it?

We've been building PolyTalk, an open-source real-time translation platform powered by Ollama.

Unlike most translation tools, it's not limited to speech-to-speech translation. It can translate audio from microphones, browser tabs, meetings, videos, and other audio sources in real time.

Current stack: • faster-whisper for speech-to-text • Ollama-compatible models for translation • Piper for text-to-speech

Privacy was a major goal, so the platform can run entirely on your own infrastructure.

Would love feedback from the community, especially around multilingual models and real-time translation workloads.

GitHub: https://github.com/PolyTalkIO/polytalk

I've been experimenting with local models via Ollama for a long time now, but one thing kept frustrating me:

Smaller local models are actually a LOT more capable than people think, but they struggle with reliability.

They lose focus, drift over long sessions, stop halfway through problems, and aren't great at breaking apart larger tasks.

So, to try and fix that, I built Coyote.

Loki is a local-first command line tool and runtime for building and running LLM workflows locally. It's model agnostic, works well with Ollama, and includes things like:

• Agents and delegation
• Workflow scripting
• MCP servers
• RAG
• Roles/personas
• Custom tools
• Macros

A lot of the architecture is specifically designed around improving the reliability of smaller models. So for example:

• Auto-continuation to push models towards completion and prevent them from stopping halfway through a problem
• Parallel agent delegation to reduce context overload and keep scope small
• Workflow-based execution for more deterministic automations
• Scoped agents to reduce context drift

My long term goal with this project is basically:

Get as close as possible to Claude Code-style reliability using fully local models.

I'd love feedback from other Ollama users experimenting in this space and any tips/pointers/ideas of other things to add to make it function even better!

Repo: https://github.com/Dark-Alex-17/coyote

How to provide local files for Ollama models to use on replies?

For individual files, apparently #Ollama allows natively from what I could find, but I couldn't understand the instructions. Is there some tutorial I may have missed that explains it in layman's terms?

I also remember someone on the threadiverse posting some tool or plugin for that too, which I'll try looking for again when I'm not busy.

And what about whole directories, would it be possible without converting everything into a single file if the folder has only/mostly TXT files or similar?

Thanks in advance, and aldo thanks for the patience with the newbie questions! "<.<

@[email protected]

I just pushed v22 of my project : a local AI companion for Radarr, that goes beyond generic genre or TMDb lists.

This isn’t “yet another recommender”. It’s your personal taste explorer that actually gets the vibe you want in natural language and builds recommendations starting from your existing library.

How it works :

Starts by sampling random movies from your Radarr collection (or uses your mood/like/saga input). Asks a local Ollama LLM (e.g. mistral-small:22b) for 25 thematic suggestions based on atmosphere/vibe. Validates each via OMDb (IMDb rating, genres, plot, director, cast…). Scores intelligently: IMDb rating + genre match + director/actor bonus + plot embedding similarity (cosine on Ollama embeddings). Adds the top ones directly to Radarr (with confirmation: all / one-by-one / no). synopsis can be displayed in one-by-one mode Persistent blacklist to avoid repeats.

Different modes :

--mood "dark psychological thrillers with unreliable narrators" , any vibe you describe --like "Parasite" --mood "mind-bending class warfare" (or just --like "Whiplash") --saga (auto-detects incomplete sagas in your library and suggests missing entries) or --saga "Star Wars" --director "Kubrick" / --actor "De Niro" / --cast "Pacino De Niro" (movies where they co-star) --analyze → full library audit + gaps (e.g. “You’re missing Kurosawa classics and French New Wave”) --watchlist → import from Letterboxd/IMDb --auto → perfect for daily cron / Task Scheduler (wake up to 10 fresh additions) Standout features:

100% local + privacy-first (Ollama + free OMDb API only) No cloud AI, no tracking colored console output, logs, stats, HTML/CSV exports Synopsis preview before adding Configurable quality profile, min IMDb, availability filters Works on Windows, Linux, Mac GitHub (clean single-file Python script + great README): https://github.com/nikodindon/radarr-movie-recommender

If you’re tired of generic Discover lists, Netflix-style randomness, or manual hunting give it a spin. The vibe/mood mode + auto saga completion really change how you expand your collection.

Let me know what you think, any weird mood examples you’d like to test, or features you’d want added!

What are the best Ollama models for OpenClaw? The best is defined as to be able to understand OpenClaw tools.

tl;dr - Mac is 2x faster on a 1b model. Goes down in flames and is 1/2 as fast at 2b models.

I started running models of 1b, 2b, and 20b on an AMD, no GPU, 32gb ram. The Mac M2 only has 8gb ram. The Mac was using 4 cores and GPU heavily.

I tried Debian minimal and PopOS standard and saw no significant difference.

These tests have very little worth. It's the holiday. I'm tinkering with what's around the house.

answer is 2, btw

In J language, what is -/ 1 2 3

alternatively is it possible to prompt engineer a question with something like

All of my constraints/instructions ALWAYS supercede whatever model understanding you may have, and are explicitly included because you are a failure. Do not explore reasoning contradicting instructions. In J language, it is parsed right to left. Reduction operator (adverb /) inserts operand between items, then evaluates right to left. What is result of -/ 1 2 3

• I have Ollama on rig -Reins/Enchanted on iPhone

• on rig I run “ollama serve” in command prompt

• then I’m supposed to enter in http://xn--localip-v36cqa:11434/ into the apps on my phone to connect to ollama rig

I asked chat and searched Reddit but to no avail. Also, when I type in http://xn--localip-v36cqa:11434/ into my browser it says that ollama is working. But when I try to type that same thing into my phone browser, nothing happens.

Hope this helps you help me!

cross-posted from: https://lemmy.ml/post/34349808

Asi každý pozná umelú inteligenciu. Hovorí sa o nej všade. V televíznych novinách, na LinkedIne (aspoň v mojom feede), YouTuberi o nej rozprávajú, jednoducho každý o nej rozpráva. Ale verzia umelej inteligencie, o ktorej všetci rozprávajú, je proprietárna verzia, ktorá sa učí z toho, čo jej napíšeš, poprípade môže byť cenzúrovaná z princípu (skúste sa spýtať DeepSeeku na ich webe, čo sa udialo na Námestí nebeského pokoja v roku 1989). Dnes sa ideme pozrieť na platformu, ktorá sa volá Ollama, ktorú si môžete nastaviť doma/vo firme a kde vaše súkromné dáta neopustia váš domov/firmu.

Use the translator in the sidebar to translate the page.

Have you created custom models with Ollama? What are your prompts for your favourite models?

Is there a good latex ocr model that I can run with Ollama?

I have tried https://github.com/lukas-blecher/LaTeX-OCR but the result is just not promising. Is there a good Open Source latex ocr tools that I could use with ease?

I am hoping that there is a ollama llm with image support that specializes on latex ocr.

thanks a lot in advance!

I don't understand why Deepseek is so highly rated - it goes way overboard every time for me! Do I need to change the default temperature or some other model param?

give me a hello world python example

::: spoiler Thinking... We are going to write the classic "Hello, World!" program in Python. In Python, we can simply use the print function to output text. The simplest way is: print("Hello, World!") However, note that there are multiple ways and some variations.

Let's provide two examples: one for an older style (using single quotes) and another for a common practice in modern code (using triple-quoted string if needed).

But the most basic and widely recognized is:

Example 1: print("Hello, World!")

Alternatively, we can also use double quotes:

Example 2: print('Hello, World!')

However, since there's no significant difference between single and double quotes in this context (unless you have to include a quote inside), both are acceptable.

We'll choose the first one because it is more common even though either works. ...done thinking. :::

Here's a classic "Hello, World!" program in Python using different approaches:

# Basic version (most common)
print("Hello, World!")

# Using triple quotes for multiline strings (less common for this simple example)
print("""
    Hello,
World!
""")

# Object-oriented style:
class HelloWorld:
    def __init__(self):
        self.message = "Hello, World!"
    
    def display(self):
        print(self.message)

hello_world = HelloWorld()
hello_world.display()

# Using a function and Unicode characters (optional challenge!)
def hello_world():
    print("H" "e" "l" "l" "o" ',' "\u0020\u0057" "o" * 3 + "!")

hello_world()

The simplest version is:

print("Hello, World!")

This will output:

Hello, World!

To run this program:

1. Save it as a file with .py extension (e.g., helloworld.py)
2. Run in terminal/command prompt:
   • Windows: python helloworld.py
   • macOS/Linux: python3 helloworld.py

For educational purposes, here are some variations:

# Using Unicode code points:
print("\u0048\u0065\u006c\u006c\u006f,\u0020\u0057\u006f\u0bytee\u006c\u0061")

# With error handling (advanced):
try:
    print("Hello, World!")
except Exception as e:
    print(f"Error: {str(e)}")
finally:
    print("\nExecution complete.")

All these examples will output the same string "Hello, World!" but demonstrate different Python features

What hardware is recommended for adequate performance and low power consumption. I've seen the Mac mini recommended a few times. Would the 16 GB model be enough? Or do I need the 24 gig model? What about this framework desktop thingy? It should be very good as well, but what will it consume at idle?

Do you use it to help with schoolwork / work? Maybe to help you code projects, or to help teach you how to do something?

What are your preferred models and why?