mirror of
https://github.com/open-webui/pipelines
synced 2025-05-11 08:01:08 +00:00
34 lines
1.0 KiB
Python
34 lines
1.0 KiB
Python
from typing import List, Union, Generator
|
|
from schemas import OpenAIChatMessage
|
|
|
|
from llama_index.embeddings.ollama import OllamaEmbedding
|
|
from llama_index.llms.ollama import Ollama
|
|
from llama_index.core import Settings
|
|
|
|
|
|
Settings.embed_model = OllamaEmbedding(
|
|
model_name="nomic-embed-text",
|
|
base_url="http://localhost:11434",
|
|
)
|
|
Settings.llm = Ollama(model="llama3")
|
|
|
|
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
|
|
|
|
documents = SimpleDirectoryReader("./data").load_data()
|
|
index = VectorStoreIndex.from_documents(documents)
|
|
|
|
|
|
def get_response(
|
|
user_message: str, messages: List[OpenAIChatMessage]
|
|
) -> Union[str, Generator]:
|
|
# This is where you can add your custom RAG pipeline.
|
|
# Typically, you would retrieve relevant information from your knowledge base and synthesize it to generate a response.
|
|
|
|
print(messages)
|
|
print(user_message)
|
|
|
|
query_engine = index.as_query_engine(streaming=True)
|
|
response = query_engine.query(user_message)
|
|
|
|
return response.response_gen
|