在LlamaIndex抽象层中自定义LLM

from llama_index.core import Settings, VectorStoreIndex, SimpleDirectoryReader
from llama_index.llms.openai import OpenAI

# define LLM
llm = OpenAI(temperature=0.1, model="gpt-4o-mini")

# change the global default LLM
Settings.llm = llm

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

# build index
index = VectorStoreIndex.from_documents(documents)

# locally override the LLM
query_engine = index.as_query_engine(llm=llm)
response = query_engine.query(
    "What did the author do after his time at Y Combinator?"
)

from typing import Optional, List, Mapping, Any

from llama_index.core import SimpleDirectoryReader, SummaryIndex
from llama_index.core.callbacks import CallbackManager
from llama_index.core.llms import (
    CustomLLM,
    CompletionResponse,
    CompletionResponseGen,
    LLMMetadata,
)
from llama_index.core.llms.callbacks import llm_completion_callback
from llama_index.core import Settings


class OurLLM(CustomLLM):
    context_window: int = 3900
    num_output: int = 256
    model_name: str = "custom"
    dummy_response: str = "My response"

    @property
    def metadata(self) -> LLMMetadata:
        """Get LLM metadata."""
        return LLMMetadata(
            context_window=self.context_window,
            num_output=self.num_output,
            model_name=self.model_name,
        )

    @llm_completion_callback()
    def complete(self, prompt: str, **kwargs: Any) -> CompletionResponse:
        return CompletionResponse(text=self.dummy_response)

    @llm_completion_callback()
    def stream_complete(
        self, prompt: str, **kwargs: Any
    ) -> CompletionResponseGen:
        response = ""
        for token in self.dummy_response:
            response += token
            yield CompletionResponse(text=response, delta=token)


# define our LLM
Settings.llm = OurLLM()

# define embed model
Settings.embed_model = "local:BAAI/bge-base-en-v1.5"


# Load the your data
documents = SimpleDirectoryReader("./data").load_data()
index = SummaryIndex.from_documents(documents)

# Query and print response
query_engine = index.as_query_engine()
response = query_engine.query("<query_text>")
print(response)