Ollama embedder not working

[BeagleByte]

Hi,
this is my code for the embedder:

embedder = OllamaEmbedder(id="nomic-embed-text",
    host="http://<REMOTE-IP>:11434",
                          dimensions=768)

vector_db = Qdrant(
    collection=collection_name,
    url=qdrant_url,
    search_type=SearchType.vector,
    embedder=embedder
)
asyncio.run(knowledge_base.add_content_async(
    path="ebooks/Bug Bounty Bootcamp The Guide to Finding and Reporting Web Vulnerabilities by Vickie Li.pdf",
    reader=PDFReader(
        name="Semantic Chunking Reader",
        chunking_strategy=SemanticChunking(
            embedder=embedder,  # Use same Agno embedder for chunking
            chunk_size=1000,
            similarity_threshold=0.5
        ))
))

I got this error:
ValueError: Failed to load embeddings via SentenceTransformerEmbeddings after registry/fallback failure: sentence-transformers/nomic-embed-text is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo either by logging in with hf auth login or by passing token=<your_token>

Please help me.

[BeagleByte]

Further tests with another config:

import asyncio
import os

from agno.agent import Agent
from agno.knowledge.chunking.fixed import FixedSizeChunking
from agno.knowledge.embedder.ollama import OllamaEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reader.pdf_reader import PDFReader
from agno.models.ollama import Ollama
from agno.vectordb.qdrant import Qdrant
from dotenv import load_dotenv, find_dotenv

load_dotenv(find_dotenv())



qdrant_url = os.getenv("QDRANT_URL")
collection_name = "agno-bug-bounty"
embedder = OllamaEmbedder(id="embeddinggemma",
                          host="http://<REMOTE-IP>:11434",dimensions=768)

# create the qdrant vector store instance
vector_db = Qdrant(
    collection=collection_name,
    url=qdrant_url,
)

knowledge_base = Knowledge(
    vector_db=vector_db,
)


asyncio.run(knowledge_base.add_content_async(
    path="ebooks/Bug Bounty Bootcamp The Guide to Finding and Reporting Web Vulnerabilities by Vickie Li.pdf",
    reader=PDFReader(
        name="Document Chunking Reader",
        chunking_strategy=FixedSizeChunking(),
        metadata={"author": "Vickie Li"},
    ),
))


# Create an agent with knowledge
agent = Agent(
    model=Ollama(id="ministral-3:3b",host="<REMOTE-IP>:11434"),
    knowledge=knowledge_base,
    # Enable automatic knowledge search
    # search_knowledge=True,
    debug_mode=False,
    search_knowledge=True,
    instructions=[
        "Your are Bug Bounty Assistant",
        "You have access to a knowledge base about bug bounty hunting",
        "please consult the knowledge base to answer user questions accurately"
    ]
)

# Test your knowledge-powered agent
if __name__ == "__main__":
    # Your agent will automatically search its knowledge to answer
    # stream = agent.run("Bug Bounty", stream=True)

    # Consume the streaming response
    agent.print_response(
        "Who is Vickie?", markdown=True
    )

This simple question give no correct answer, other RAG setup with spring ai or Open WebUI got the question right, so can someone explain me what is wrong?