Proveedores IA

Añadir Proveedor
Deepseek Ollama
URL http://localhost:11434
Modelo deepseek-r1:7b
Max Tokens 4096
Temperatura 0,1
RAG Providers
nomic
Editar
Guía Rápida
Ollama
ollama pull deepseek-coder:6.7b
ollama serve
URL: http://localhost:11434
LM Studio

Inicia LM Studio con servidor local habilitado.

URL: http://localhost:1234
GGUF (llama.cpp)
./server -m deepseek-coder.gguf
URL: http://localhost:8080

RAG Providers Local

Add RAG Provider
nomic Activo
URL http://localhost:11434
Modelo nomic-embed-text
Collection wasi-fpga-code
Chunk 512+64 chars · top_k=4
Indexed 280 chunks
Last index 13/05/2026 12:02
Editar
RAG Quick Setup (Nomic + Ollama)
1.Pull the embedding model
ollama pull nomic-embed-text

nomic-embed-text produces 768-dim vectors optimised for code retrieval.

2.Add provider & rebuild index

Create a RAG Provider pointing to your Ollama URL, then click Rebuild Index.The assistant will automatically use retrieved snippets as context.