How to setup AI tagging with local ollama properly?
Hi, I am not getting the AI tagging with ollama running.
Ollama is installed locally (no docker) and llama3.1 is installed. Directly calling ollama runs fine.
Thx for your help!
My .env file:
HOARDER_VERSION=release
NEXTAUTH_SECRET=9xxxxL
MEILI_MASTER_KEY=Uxxxxq
NEXTAUTH_URL=http://localhost:3000
OLLAMA_BASE_URL=http://host.docker.internal:11434
INFERENCE_TEXT_MODEL=llama3.1
INFERENCE_IMAGE_MODEL=llava
The error I am getting is:
TypeError: fetch failed
at node:internal/deps/undici/undici:13185:13
at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
at async post (/app/apps/workers/node_modules/.pnpm/ollama@0.5.9/node_modules/ollama/dist/shared/ollama.9c897541.cjs:114:20)
at async Ollama.processStreamableRequest (/app/apps/workers/node_modules/.pnpm/ollama@0.5.9/node_modules/ollama/dist/shared/ollama.9c897541.cjs:232:25)
at async OllamaInferenceClient.runModel (/app/apps/workers/inference.ts:2:3086)
at async OllamaInferenceClient.inferFromText (/app/apps/workers/inference.ts:2:3790)
at async inferTagsFromText (/app/apps/workers/openaiWorker.ts:6:2663)
at async inferTags (/app/apps/workers/openaiWorker.ts:6:2886)
at async Object.runOpenAI [as run] (/app/apps/workers/openaiWorker.ts:6:6316)
at async Runner.runOnce (/app/apps/workers/node_modules/.pnpm/@hoarder+queue@file+packages+queue/node_modules/@hoarder/queue/runner.ts:2:2567)
Ollama is installed locally (no docker) and llama3.1 is installed. Directly calling ollama runs fine.
Thx for your help!
My .env file:
HOARDER_VERSION=release
NEXTAUTH_SECRET=9xxxxL
MEILI_MASTER_KEY=Uxxxxq
NEXTAUTH_URL=http://localhost:3000
OLLAMA_BASE_URL=http://host.docker.internal:11434
INFERENCE_TEXT_MODEL=llama3.1
INFERENCE_IMAGE_MODEL=llava
The error I am getting is:
TypeError: fetch failed
at node:internal/deps/undici/undici:13185:13
at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
at async post (/app/apps/workers/node_modules/.pnpm/ollama@0.5.9/node_modules/ollama/dist/shared/ollama.9c897541.cjs:114:20)
at async Ollama.processStreamableRequest (/app/apps/workers/node_modules/.pnpm/ollama@0.5.9/node_modules/ollama/dist/shared/ollama.9c897541.cjs:232:25)
at async OllamaInferenceClient.runModel (/app/apps/workers/inference.ts:2:3086)
at async OllamaInferenceClient.inferFromText (/app/apps/workers/inference.ts:2:3790)
at async inferTagsFromText (/app/apps/workers/openaiWorker.ts:6:2663)
at async inferTags (/app/apps/workers/openaiWorker.ts:6:2886)
at async Object.runOpenAI [as run] (/app/apps/workers/openaiWorker.ts:6:6316)
at async Runner.runOnce (/app/apps/workers/node_modules/.pnpm/@hoarder+queue@file+packages+queue/node_modules/@hoarder/queue/runner.ts:2:2567)
