AI & Jellyfin - Revision history

Wikisailor: /* Jellyfin Installation */

2026-04-20T18:53:06Z

Jellyfin Installation

← Older revision		Revision as of 18:53, 20 April 2026
Line 50:		Line 50:
	===Jellyfin Installation===		===Jellyfin Installation===

	To give the media server plenty of storage we have mounted a 3TB data drive at /mnt/jellyfin/ to store all of the media files, we have another drive at /mnt/docker_data to hold all of the configuration data for the containers. We had some difficulty with a left over jellyfin container instalation so we called this container jellyfin-new. The yaml file for "jellyfin-new" is as follows.		To give the media server plenty of storage we have mounted a 3TB data drive at /mnt/jellyfin/ to store all of the media files, we have another drive at /mnt/docker_data to hold all of the configuration data for the containers. We had some difficulty with a left over jellyfin container instalation so we called this container jellyfin-new to start with. The yaml file for "jellyfin-new" is as follows.

	services:		services:

Wikisailor: /* Docker Applications installed on Quince */

2026-04-20T18:51:19Z

Docker Applications installed on Quince

← Older revision		Revision as of 18:51, 20 April 2026
Line 5:		Line 5:
	== Docker Applications installed on Quince ==		== Docker Applications installed on Quince ==

	We are going to need to install several applications that will share the GPU. The first will Dockge so that any new containers can be managed easily. We will also need to install Ollama so that we can run LLMs easily. Then to make use of the data archive we can use AnythingLLM.		We are going to need to install several applications that will share the GPU. The first will be Dockge so that any new containers can be managed easily. We will also need to install Ollama so that we can run LLMs easily. Then to make use of the data archive we can use AnythingLLM.

	==Installation Strategy==		==Installation Strategy==

Wikisailor: /* AnythingLLM */

2026-02-11T17:39:08Z

AnythingLLM

← Older revision		Revision as of 17:39, 11 February 2026
Line 181:		Line 181:
	* It should be mentioned that the network isolation provided by both Ollama and Anythingllm residing on the ai-network means AnythingLLM can reach the LLM at http://ollama:11434. This internal traffic never touches the main LAN, keeping the AI conversations extremely fast and private from other devices on the local network.		* It should be mentioned that the network isolation provided by both Ollama and Anythingllm residing on the ai-network means AnythingLLM can reach the LLM at http://ollama:11434. This internal traffic never touches the main LAN, keeping the AI conversations extremely fast and private from other devices on the local network.



	The AnythingLLM can be installed with the name "anythingllm" and the yaml file below		The AnythingLLM can be installed with the name "anythingllm" and the yaml file below
Line 214:		Line 213:

	====📂The ArchiveBox "Read-Only" Link====		====📂The ArchiveBox "Read-Only" Link====

	The volume mapping for ArchiveBox is very clever		The volume mapping for ArchiveBox is very clever
	/mnt/archive_data/archivebox:/app/server/storage/documents/archivebox:ro		/mnt/archive_data/archivebox:/app/server/storage/documents/archivebox:ro
Line 220:		Line 218:
	* The :ro flag: This is critical. It ensures AnythingLLM can read the archives to "learn" from them, but it can never accidentally delete or modify the ArchiveBox data.		* The :ro flag: This is critical. It ensures AnythingLLM can read the archives to "learn" from them, but it can never accidentally delete or modify the ArchiveBox data.
	* Visibility: In the AnythingLLM UI, when we go to "Upload Documents," we will see a folder named archivebox. We can then move those files into your Workspace to start chatting with our archived websites.		* Visibility: In the AnythingLLM UI, when we go to "Upload Documents," we will see a folder named archivebox. We can then move those files into your Workspace to start chatting with our archived websites.

			====🛠️Environment & Permissions====
			* '''The .env file:''' We are mounting /mnt/docker_data/anythingllm/.env. Before we run docker compose up, we make sure that file actually exists (even if it's empty) or Docker might create it as a folder by mistake.
			** Quick fix: touch /mnt/docker_data/anythingllm/.env
			* SYS_ADMIN Capability: This is required by AnythingLLM because it uses a technology called Puppeteer to scrape websites. Without this "cap_add," the document scraper will likely fail.

			====📊 Quince GPU Status (Ollama + AnythingLLM)====
			Ollama Memory: 4900MiB / 16311MiB
			The "Quiet" Documentation: Now that AnythingLLM is joining the party on Quince:
			* VRAM: AnythingLLM itself uses almost zero VRAM. It just sends instructions to Ollama.
			* Concurrency: You can have Jellyfin transcoding a movie, Ollama running Mistral, and AnythingLLM scraping a document all at once on that 5060 Ti.

Wikisailor: /* AnythingLLM */

2026-02-11T17:32:45Z

AnythingLLM

@@ Line 171: / Line 171: @@
 ===AnythingLLM ===
 The AnythingLLM can be installed with the name "anythingllm" and the yaml file below
@@ Line 194: / Line 205: @@
     ai-network:
       external: true

Wikisailor: /* AnythingLLM */

2026-02-11T12:12:27Z

AnythingLLM

← Older revision		Revision as of 12:12, 11 February 2026
Line 171:		Line 171:

	===AnythingLLM ===		===AnythingLLM ===

			The AnythingLLM can be installed with the name "anythingllm" and the yaml file below
			services:
			anythingllm:
			image: mintplexlabs/anythingllm:latest
			container_name: anythingllm
			ports:
			- 3001:3001
			cap_add:
			- SYS_ADMIN
			environment:
			- STORAGE_DIR=/app/server/storage
			volumes:
			- /mnt/docker_data/anythingllm:/app/server/storage
			- /mnt/docker_data/anythingllm/.env:/app/server/.env
			# This links the Blackberry NFS mount into AnythingLLM
			- /mnt/archive_data/archivebox:/app/server/storage/documents/archivebox:ro
			networks:
			- ai-network
			restart: unless-stopped
			networks:
			ai-network:
			external: true

Wikisailor: /* Loading a model via SSH */

2026-02-11T12:02:37Z

Loading a model via SSH

← Older revision		Revision as of 12:02, 11 February 2026
Line 152:		Line 152:
	\|Qwen2.5-Coder \|\| ~4.7 GB \|\| Good for coding in Go		\|Qwen2.5-Coder \|\| ~4.7 GB \|\| Good for coding in Go
	\|-		\|-
	\|GPT-OSS:20B \|\| 13 GB \|\|		\|GPT-OSS:20B \|\| ~13 GB \|\|
	\|-		\|-
	\|gemma3:12b \|\| 8.1 GB \|\|		\|gemma3:12b \|\| ~8.1 GB \|\|
	\|}		\|}

Wikisailor: /* Loading a model via SSH */

2026-02-11T12:02:08Z

Loading a model via SSH

← Older revision		Revision as of 12:02, 11 February 2026
Line 134:		Line 134:
	* To check what is currently on your disk, complete with the version and size run:		* To check what is currently on your disk, complete with the version and size run:
	docker exec -it ollama ollama list		docker exec -it ollama ollama list



	{\| class="wikitable"		{\| class="wikitable"
Line 151:		Line 149:
	\|-		\|-
	\|Command R (35B) \|\| ~20 GB \|\| The Stretch Goal. At 4-bit quantization, this might fit or spill slightly into system RAM. It’s incredibly smart for document analysis.		\|Command R (35B) \|\| ~20 GB \|\| The Stretch Goal. At 4-bit quantization, this might fit or spill slightly into system RAM. It’s incredibly smart for document analysis.
			\|-
			\|Qwen2.5-Coder \|\| ~4.7 GB \|\| Good for coding in Go
			\|-
			\|GPT-OSS:20B \|\| 13 GB \|\|
			\|-
			\|gemma3:12b \|\| 8.1 GB \|\|
	\|}		\|}

Wikisailor: /* Loading a model via SSH */

2026-02-11T11:53:33Z

Loading a model via SSH

← Older revision		Revision as of 11:53, 11 February 2026
Line 165:		Line 165:
	docker exec -it ollama nvidia-smi		docker exec -it ollama nvidia-smi
	Look at the Memory-Usage and the Processes list at the bottom. It should show ollama using ~4.5 GB or ~5.2 GB of VRAM, it is successfully running on the GPU. If it stays at 4MiB / 16311MiB, it’s "hallucinating" on your CPU instead, and we’d need to check the drivers.		Look at the Memory-Usage and the Processes list at the bottom. It should show ollama using ~4.5 GB or ~5.2 GB of VRAM, it is successfully running on the GPU. If it stays at 4MiB / 16311MiB, it’s "hallucinating" on your CPU instead, and we’d need to check the drivers.

			===AnythingLLM ===

Wikisailor: /* Loading a model via SSH */

2026-02-11T11:48:39Z

Loading a model via SSH

← Older revision		Revision as of 11:48, 11 February 2026
Line 161:		Line 161:
	docker exec -it ollama ollama run mistral:7b		docker exec -it ollama ollama run mistral:7b
	docker exec -it ollama ollama run llama3.1:8b		docker exec -it ollama ollama run llama3.1:8b

			* How to verify it's in the GPU (The "Acid Test"). This is the most important part for the 5060 Ti. While chatting with a model in one SSH window, open a second SSH window and run:
			docker exec -it ollama nvidia-smi
			Look at the Memory-Usage and the Processes list at the bottom. It should show ollama using ~4.5 GB or ~5.2 GB of VRAM, it is successfully running on the GPU. If it stays at 4MiB / 16311MiB, it’s "hallucinating" on your CPU instead, and we’d need to check the drivers.

Wikisailor: /* Ollama installation */

2026-02-11T11:35:05Z

Ollama installation

← Older revision		Revision as of 11:35, 11 February 2026
Line 120:		Line 120:

	* Note that the device driver is set to nvidia		* Note that the device driver is set to nvidia
			* To verify it's in the GPU
			docker exec -it ollama nvidia-smi

	====Loading a model via SSH ====		====Loading a model via SSH ====