Llama_index利用本地大模型工具ollama（CPU）

基于ollama的本地大模型的LlamaIndex示例代码

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
from llama_index.core.embeddings import resolve_embed_model
from llama_index.llms.ollama import Ollama

import logging
import sys

logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

documents = SimpleDirectoryReader("data").load_data()

# bge embedding model
Settings.embed_model = resolve_embed_model("local:/Users/leicq/ai_pychat/BAAI_bge-base-zh-v1.5")

# ollama
Settings.llm = Ollama(model="llama2-chinese", request_timeout=30.0)

import os.path
from llama_index.core import (
    VectorStoreIndex,
    SimpleDirectoryReader,
    StorageContext,
    load_index_from_storage,
)

# check if storage already exists
PERSIST_DIR = "./storage"
if not os.path.exists(PERSIST_DIR):
    # load the documents and create the index
    documents = SimpleDirectoryReader("data").load_data()
    index = VectorStoreIndex.from_documents(documents)
    # store it for later
    index.storage_context.persist(persist_dir=PERSIST_DIR)
else:
    # load the existing index
    storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
    index = load_index_from_storage(storage_context)

# Either way we can now query the index
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
print(response)