txtai-llama-3.2.py

from txtai import Embeddings, RAG

# Load embeddings index
embeddings = Embeddings()
embeddings.load(provider="huggingface-hub", container="neuml/txtai-wikipedia")

template = """
Answer the following question using the provided context.

Question:
{question}

Context:
{context}

Answer: 
"""

# Create and run pipeline
rag = RAG(
  embeddings, 
  "hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF/llama-3.2-1b-instruct-q4_k_m.gguf",
  template=template
)

rag("Tell me about Mars in a short sentence")["answer"]