# Beginners

**URL:** /static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fc%2Fbeginners%2F5.md

[Latest](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Flatest.md) · [Categories](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fcategories.md)

---

## [How To Request Support](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-request-support%2F3128)

<div class="topic-metadata">

**Author:** [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Replies:** 2\
**Last updated:** [January 31, 2023, 10:29am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-request-support%2F3128 "2023-01-31T10:29:08Z")

</div>

This post is a copy of the new ISSUES document we recently merged about how to efficiently request support for one of the Hugging Face libraries. It’s designed with GitHub issues in mind, but it’s a useful read for gener…

---

## [How to ask questions on the forum?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-ask-questions-on-the-forum%2F54)

<div class="topic-metadata">

**Author:** [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Replies:** 22\
**Last updated:** [July 14, 2026, 8:29am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-ask-questions-on-the-forum%2F54 "2026-07-14T08:29:12Z")

</div>

Hi there and welcome on the HuggingFace forums! Here are a few guidelines before you make your first post, but the goal is to create a wide discussion space with the NLP community, so don’t hesitate to break them if you…

---

## [About the Hugging Face Forums](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fabout-the-hugging-face-forums%2F24)

<div class="topic-metadata">

**Author:** [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Replies:** 1\
**Last updated:** [May 6, 2024, 6:31pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fabout-the-hugging-face-forums%2F24 "2024-05-06T18:31:17Z")

</div>

You can login using your huggingface.co credentials. This forum is powered by Discourse and relies on a trust-level system. As a new user, you’re temporarily limited in the number of topics and posts you can create. To …

---

## [Setup for local ai models on apple silicon](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsetup-for-local-ai-models-on-apple-silicon%2F192253)

<div class="topic-metadata">

**Author:** [@zerix0](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fzerix0)%5C
**Replies:** 1\
**Last updated:** [November 21, 2026, 8:15am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsetup-for-local-ai-models-on-apple-silicon%2F192253 "2026-11-21T08:15:26Z")

</div>

I’m on an m5 pro 48gb, i’m using qwen 3.8 27b on ollama and i think i’m missing a lot because i get some critical memory spikes sometimes while sing 125k context in Pi Harness if i remember right (haven’t spin out a ses…

---

## [Looking for a good local model for LaTeX coding/ debugging on limited hardware](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flooking-for-a-good-local-model-for-latex-coding-debugging-on-limited-hardware%2F192236)

<div class="topic-metadata">

**Author:** [@Rocky07e](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FRocky07e)%5C
**Replies:** 1\
**Last updated:** [November 21, 2026, 5:34am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flooking-for-a-good-local-model-for-latex-coding-debugging-on-limited-hardware%2F192236 "2026-11-21T05:34:44Z")

</div>

Hi everyone, I’m looking for some advice on choosing a good local LLM for LaTeX editing and coding. My laptop isn’t particularly powerful, so I’m trying to find something that runs reasonably well with the following sp…

---

## [Terse abstention qwen 3 4B](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fterse-abstention-qwen-3-4b%2F191481)

<div class="topic-metadata">

**Author:** [@LuzCommand](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FLuzCommand)%5C
**Replies:** 9\
**Last updated:** [November 21, 2026, 1:26am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fterse-abstention-qwen-3-4b%2F191481 "2026-11-21T01:26:07Z")

</div>

Here is my first go at a small terse abstainer. Just curious if anyone else is trying to do this?

---

## [The product review that issued a 100% discount](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fthe-product-review-that-issued-a-100-discount%2F192108)

<div class="topic-metadata">

**Author:** [@Vivekwritesdaily](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FVivekwritesdaily)%5C
**Replies:** 1\
**Last updated:** [November 21, 2026, 12:33am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fthe-product-review-that-issued-a-100-discount%2F192108 "2026-11-21T00:33:32Z")

</div>

Most people think of prompt injection as a user typing “ignore your instructions” into a chatbot. Indirect prompt injection is different: the malicious instruction is hidden inside content the AI reads, not in what the u…

---

## [Peanut v2 - A more stable Adam variant, tested on CPU only. Try it on your dataset?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpeanut-v2-a-more-stable-adam-variant-tested-on-cpu-only-try-it-on-your-dataset%2F191809)

<div class="topic-metadata">

**Author:** [@AllDirs](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAllDirs)%5C
**Replies:** 11\
**Last updated:** [November 21, 2026, 12:25am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpeanut-v2-a-more-stable-adam-variant-tested-on-cpu-only-try-it-on-your-dataset%2F191809 "2026-11-21T00:25:59Z")

</div>

Hi everyone, I just made public a small peanut project I built on a CPU-only laptop, no GPU. Repo: https://github.com/dskc/peanut Idea is simple. Peanut v2 is Adam with two changes: Damped first step: first update m…

---

## [Why AI agents can change behavior without a code change](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhy-ai-agents-can-change-behavior-without-a-code-change%2F192109)

<div class="topic-metadata">

**Author:** [@Vivekwritesdaily](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FVivekwritesdaily)%5C
**Replies:** 7\
**Last updated:** [November 20, 2026, 10:15pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhy-ai-agents-can-change-behavior-without-a-code-change%2F192109 "2026-11-20T22:15:41Z")

</div>

In traditional software, behavior changes when code changes. AI agents add another variable: the underlying model. Example: A fintech support agent runs on the same prompt and tools for months. After the model provider …

---

## [How do you decide which model to start with for a first project?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-do-you-decide-which-model-to-start-with-for-a-first-project%2F191863)

<div class="topic-metadata">

**Author:** [@michaellown](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmichaellown)%5C
**Replies:** 4\
**Last updated:** [November 20, 2026, 2:54pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-do-you-decide-which-model-to-start-with-for-a-first-project%2F191863 "2026-11-20T14:54:12Z")

</div>

Hi everyone, I am starting my first machine learning project and I am trying to figure out how to pick a model to begin with. Do you start with a small, well-known model and grow from there, or do you look for a model a…

---

## [Advice on a set up for medical transcription and note formulation](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fadvice-on-a-set-up-for-medical-transcription-and-note-formulation%2F191256)

<div class="topic-metadata">

**Author:** [@SandfishOutwit](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FSandfishOutwit)%5C
**Replies:** 6\
**Last updated:** [November 20, 2026, 11:20am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fadvice-on-a-set-up-for-medical-transcription-and-note-formulation%2F191256 "2026-11-20T11:20:47Z")

</div>

Looking for recommendations on hardware, as well as model selection. In Australia. Working as a physiotherapist. Looking for something like Heidi, but that doesn’t send data off anywhere at all. So essentially to - reco…

---

## [Running local AI models](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-local-ai-models%2F192189)

<div class="topic-metadata">

**Author:** [@pruexx](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fpruexx)%5C
**Replies:** 3\
**Last updated:** [November 20, 2026, 11:40am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-local-ai-models%2F192189 "2026-11-20T11:40:41Z")

</div>

Title: Running local AI models on an 8GB M2 Mac I have a base M2 MacBook Air, and memory gets tight pretty quickly when I have Safari and several PDFs open. I’ve been curious about trying local AI models, but I’m not su…

---

## [How internal AI assistants leak data through permissions](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-internal-ai-assistants-leak-data-through-permissions%2F192110)

<div class="topic-metadata">

**Author:** [@Vivekwritesdaily](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FVivekwritesdaily)%5C
**Replies:** 3\
**Last updated:** [November 20, 2026, 4:44am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-internal-ai-assistants-leak-data-through-permissions%2F192110 "2026-11-20T04:44:05Z")

</div>

Many companies connect AI assistants to internal drives so employees can ask questions about policies and documents. A common risk is that the assistant can access more than the person asking should see. Example: An HR …

---

## [Gradio Spaces stuck in NO\_APP\_FILE despite valid app.py and README.md](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgradio-spaces-stuck-in-no-app-file-despite-valid-app-py-and-readme-md%2F192099)

<div class="topic-metadata">

**Author:** [@TomaQue](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FTomaQue)%5C
**Replies:** 2\
**Last updated:** [November 20, 2026, 3:05am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgradio-spaces-stuck-in-no-app-file-despite-valid-app-py-and-readme-md%2F192099 "2026-11-20T03:05:13Z")

</div>

Hello Hugging Face Support, I’m experiencing a persistent issue with two private Gradio Spaces on my account. Affected Spaces: https://huggingface.co/spaces/TomaQue/Akilper-Animator https://huggingface.co/spaces/…

---

## [Question please](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fquestion-please%2F192180)

<div class="topic-metadata">

**Author:** [@Denzophagee](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FDenzophagee)%5C
**Replies:** 0\
**Last updated:** [November 20, 2026, 1:42am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fquestion-please%2F192180 "2026-11-20T01:42:41Z")

</div>

I’m a VRChat Avatar Creator and I’m new here, I would like to showcase myself, share my previous work and review I got from my previous client and also advertise myself if possible I want to ask i that allows on this fo…

---

## [Help: Downloading a Plant Dataset from Baidu](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelp-downloading-a-plant-dataset-from-baidu%2F192148)

<div class="topic-metadata">

**Author:** [@zhaduchanhzz](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fzhaduchanhzz)%5C
**Replies:** 2\
**Last updated:** [November 19, 2026, 5:47pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelp-downloading-a-plant-dataset-from-baidu%2F192148 "2026-11-19T17:47:19Z")

</div>

I’m interested in using this plant dataset for my research, but unfortunately, I’m having difficulty downloading it from Baidu Netdisk because of access restrictions. Could anyone help me download the dataset from the f…

---

## [Where to share?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhere-to-share%2F176592)

<div class="topic-metadata">

**Author:** [@PathMapper](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FPathMapper)%5C
**Replies:** 5\
**Last updated:** [November 19, 2026, 3:46pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhere-to-share%2F176592 "2026-11-19T15:46:55Z")

</div>

I made a useful tool for AI but I don’t know how to build a community. I have been an unpaid caregiver for several years and though I have done so for love, I also had way too much time on my hands to think. Last June …

---

## [What's your setup for running models locally?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhats-your-setup-for-running-models-locally%2F192128)

<div class="topic-metadata">

**Author:** [@ashalwi](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fashalwi)%5C
**Replies:** 4\
**Last updated:** [November 21, 2026, 3:53am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhats-your-setup-for-running-models-locally%2F192128 "2026-11-21T03:53:17Z")

</div>

Do you run your models locally on your laptop, or do you use a dedicated machine/server for inference? I’ve experimented with running several small models on my MacBook Pro using Ollama, but found the performance rather…

---

## [Is hf download really auto resume](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fis-hf-download-really-auto-resume%2F175105)

<div class="topic-metadata">

**Author:** [@saycchai](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsaycchai)%5C
**Replies:** 4\
**Last updated:** [November 19, 2026, 12:05pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fis-hf-download-really-auto-resume%2F175105 "2026-11-19T12:05:02Z")

</div>

I download the gemma4 models and I use “hf download” and disconnected, I hf download again and get this message: hf download google/gemma-4-26b-a4b-it --token Fetching 11 files: 0%| …

---

## [Vetting an open model before deployment](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fvetting-an-open-model-before-deployment%2F191584)

<div class="topic-metadata">

**Author:** [@VivekNotes](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FVivekNotes)%5C
**Replies:** 4\
**Last updated:** [November 19, 2026, 10:43am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fvetting-an-open-model-before-deployment%2F191584 "2026-11-19T10:43:56Z")

</div>

A small team wanted to replace a paid API with an open model from the Hub to cut costs. The model looked great in a notebook demo and ranked well on public leaderboards. Before switching, they read the model card, which…

---

## [Topped up $10 to buy more gpu but it wont let me use it](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftopped-up-10-to-buy-more-gpu-but-it-wont-let-me-use-it%2F192127)

<div class="topic-metadata">

**Author:** [@AbiWood89](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAbiWood89)%5C
**Replies:** 0\
**Last updated:** [November 19, 2026, 7:01am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftopped-up-10-to-buy-more-gpu-but-it-wont-let-me-use-it%2F192127 "2026-11-19T07:01:41Z")

</div>

Doing an art project and creating video clips, ran out of daily free so i topped up but cannot but or do anything still, can anyone help?

---

## [Build AI Agent for Social Media Posting](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-ai-agent-for-social-media-posting%2F134360)

<div class="topic-metadata">

**Author:** [@woodenman85](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fwoodenman85)%5C
**Replies:** 5\
**Last updated:** [November 18, 2026, 5:04pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-ai-agent-for-social-media-posting%2F134360 "2026-11-18T17:04:29Z")

</div>

I don’t know how. I tried Chat GPT for help but was not getting what I needed. Any advice? I’m wondering how to have one running for my Life Insurance business…

---

## [Need advice on building a chatbot](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fneed-advice-on-building-a-chatbot%2F191880)

<div class="topic-metadata">

**Author:** [@ashalwi](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fashalwi)%5C
**Replies:** 8\
**Last updated:** [November 19, 2026, 7:09am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fneed-advice-on-building-a-chatbot%2F191880 "2026-11-19T07:09:00Z")

</div>

Hello smart people of HF! I’ve been wrestling to build a chatbot for a company project for months now. I’m not technical, and I am still learning. The use case for the chatbot/assistant is to help users seek answers fr…

---

## [Unable to subscribe to Hugging Face PRO - "A processing error occurred"](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-subscribe-to-hugging-face-pro-a-processing-error-occurred%2F192100)

<div class="topic-metadata">

**Author:** [@youssefjbilou-ma](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fyoussefjbilou-ma)%5C
**Replies:** 1\
**Last updated:** [November 18, 2026, 3:33pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-subscribe-to-hugging-face-pro-a-processing-error-occurred%2F192100 "2026-11-18T15:33:52Z")

</div>

Hello Hugging Face Team, I am trying to subscribe to the Hugging Face PRO plan ($9/month), but every payment attempt fails with the error message: “A processing error occurred.” Here is what I have already tried: Usi…

---

## [Best AI WebUi to interact with local LLM AI](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbest-ai-webui-to-interact-with-local-llm-ai%2F191856)

<div class="topic-metadata">

**Author:** [@HearthlocalAI](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FHearthlocalAI)%5C
**Replies:** 3\
**Last updated:** [November 18, 2026, 2:01am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbest-ai-webui-to-interact-with-local-llm-ai%2F191856 "2026-11-18T02:01:52Z")

</div>

Feel free to post best web app that can perform Local and hosted AI chat, Model management, LLM evaluation, Agentic coding, Agent skills, Personal AI memory, performs Web research, Voice assistant, Creative tools, Hosted…

---

## [Finding Collaborators](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinding-collaborators%2F192009)

<div class="topic-metadata">

**Author:** [@AIONWORLD](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAIONWORLD)%5C
**Replies:** 0\
**Last updated:** [November 18, 2026, 1:42am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinding-collaborators%2F192009 "2026-11-18T01:42:35Z")

</div>

AION — An Open Invitation to Help Build the Future of Cooperative Intelligence We’re looking for researchers, developers, AI enthusiasts and independent thinkers interested in helping build AION. Hello everyone! I’m t…

---

## [Using Local LLMs for fact+claim data structuring for Knowledge Graph building](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-local-llms-for-fact-claim-data-structuring-for-knowledge-graph-building%2F191923)

<div class="topic-metadata">

**Author:** [@chrishigh67](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fchrishigh67)%5C
**Replies:** 2\
**Last updated:** [November 17, 2026, 10:58pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-local-llms-for-fact-claim-data-structuring-for-knowledge-graph-building%2F191923 "2026-11-17T22:58:19Z")

</div>

I’m working on a pipeline that extracts findings from PubMed abstracts and turns them into structured evidence for a knowledge graph: which compound caused which effect, in what biological system, at what dose, and suppo…

---

## [Speech detection in records from SIP-telephony with G.729 codec](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fspeech-detection-in-records-from-sip-telephony-with-g-729-codec%2F86384)

<div class="topic-metadata">

**Author:** [@dkurdomanenko](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdkurdomanenko)%5C
**Replies:** 1\
**Last updated:** [November 17, 2026, 9:57pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fspeech-detection-in-records-from-sip-telephony-with-g-729-codec%2F86384 "2026-11-17T21:57:14Z")

</div>

I need to implement the process of additional training of a multilingual speech recognition model in such a way as to improve the quality of recognition on data received via SIP telephony (G.729 codec). Is it a good idea…

---

## [Integrating Chat in On-Premises Data Software?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fintegrating-chat-in-on-premises-data-software%2F49981)

<div class="topic-metadata">

**Author:** [@tbo81](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ftbo81)%5C
**Replies:** 2\
**Last updated:** [November 17, 2026, 6:48am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fintegrating-chat-in-on-premises-data-software%2F49981 "2026-11-17T06:48:02Z")

</div>

My task is to integrate chat functionality into on-premises data documentation and data catalog software. I need to plan a solution. I have developed a prototype using LangChain and the OpenAI API. However, this is not …

---

## [How do you design memory systems for long-running AI agents?](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-do-you-design-memory-systems-for-long-running-ai-agents%2F175584)

<div class="topic-metadata">

**Author:** [@Suhebmultani](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FSuhebmultani)%5C
**Replies:** 20\
**Last updated:** [November 16, 2026, 9:41pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-do-you-design-memory-systems-for-long-running-ai-agents%2F175584 "2026-11-16T21:41:16Z")

</div>

If an AI agent runs for a long time (like a chatbot or assistant), how do you design a system so it can remember things properly?

[Next page](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fc%2Fbeginners%2F5.md%3Fpage%3D1)
