👾打开 RAG 对接大模型的黑盒 —— 9 大隐藏问题

!pip install llama-index

# My OpenAI Key
import os
os.environ['OPENAI_API_KEY'] = ""


import logging
import sys
import requests

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

from llama_index import VectorStoreIndex, SimpleDirectoryReader
from IPython.display import Markdown, display

# download paul graham's essay
response = requests.get("https://www.dropbox.com/s/f6bmb19xdg0xedm/paul_graham_essay.txt?dl=1")
essay_txt = response.text
with open("pg_essay.txt", "w") as fp:
  fp.write(essay_txt)
  
  
  # load documents
documents = SimpleDirectoryReader(input_files=['pg_essay.txt']).load_data()


index = VectorStoreIndex.from_documents(documents)


# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine(similarity_top_k=2)

response = query_engine.query(
    "What did the author do growing up?",
)


print(response.source_nodes[0].node.get_text())

# contains the parameters that need to be tuned
param_dict = {"chunk_size": [256, 512, 1024], "top_k": [1, 2, 5]}

# contains parameters remaining fixed across all runs of the tuning process
fixed_param_dict = {
    "docs": documents,
    "eval_qs": eval_qs,
    "ref_response_strs": ref_response_strs,
}

def objective_function_semantic_similarity(params_dict):
    chunk_size = params_dict["chunk_size"]
    docs = params_dict["docs"]
    top_k = params_dict["top_k"]
    eval_qs = params_dict["eval_qs"]
    ref_response_strs = params_dict["ref_response_strs"]

    # build index
    index = _build_index(chunk_size, docs)

    # query engine
    query_engine = index.as_query_engine(similarity_top_k=top_k)

    # get predicted responses
    pred_response_objs = get_responses(
        eval_qs, query_engine, show_progress=True
    )

    # run evaluator
    eval_batch_runner = _get_eval_batch_runner_semantic_similarity()
    eval_results = eval_batch_runner.evaluate_responses(
        eval_qs, responses=pred_response_objs, reference=ref_response_strs
    )

    # get semantic similarity metric
    mean_score = np.array(
        [r.score for r in eval_results["semantic_similarity"]]
    ).mean()

    return RunResult(score=mean_score, params=params_dict)


param_tuner = ParamTuner(
    param_fn=objective_function_semantic_similarity,
    param_dict=param_dict,
    fixed_param_dict=fixed_param_dict,
    show_progress=True,
)

results = param_tuner.tune()

import os
from llama_index.postprocessor.cohere_rerank import CohereRerank

api_key = os.environ["COHERE_API_KEY"]
cohere_rerank = CohereRerank(api_key=api_key, top_n=2) # return top 2 nodes from reranker

query_engine = index.as_query_engine(
    similarity_top_k=10, # we can set a high top_k here to ensure maximum relevant retrieval
    node_postprocessors=[cohere_rerank], # pass the reranker to node_postprocessors
)

response = query_engine.query(
    "What did Elon Musk do?",
)

from llama_index.core.query_engine import RetrieverQueryEngine
from llama_index.core.response_synthesizers import CompactAndRefine
from llama_index.postprocessor.longllmlingua import LongLLMLinguaPostprocessor
from llama_index.core import QueryBundle

node_postprocessor = LongLLMLinguaPostprocessor(
    instruction_str="Given the context, please answer the final question",
    target_token=300,
    rank_method="longllmlingua",
    additional_compress_kwargs={
        "condition_compare": True,
        "condition_in_question": "after",
        "context_budget": "+100",
        "reorder_context": "sort",  # enable document reorder
    },
)

retrieved_nodes = retriever.retrieve(query_str)
synthesizer = CompactAndRefine()

# outline steps in RetrieverQueryEngine for clarity:
# postprocess (compress), synthesize
new_retrieved_nodes = node_postprocessor.postprocess_nodes(
    retrieved_nodes, query_bundle=QueryBundle(query_str=query_str)
)

print("\n\n".join([n.get_content() for n in new_retrieved_nodes]))

response = synthesizer.synthesize(query_str, new_retrieved_nodes)

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.core.output_parsers import LangchainOutputParser
from llama_index.llms.openai import OpenAI
from langchain.output_parsers import StructuredOutputParser, ResponseSchema

# load documents, build index
documents = SimpleDirectoryReader("../paul_graham_essay/data").load_data()
index = VectorStoreIndex.from_documents(documents)

# define output schema
response_schemas = [
    ResponseSchema(
        name="Education",
        description="Describes the author's educational experience/background.",
    ),
    ResponseSchema(
        name="Work",
        description="Describes the author's work experience/background.",
    ),
]

# define output parser
lc_output_parser = StructuredOutputParser.from_response_schemas(
    response_schemas
)
output_parser = LangchainOutputParser(lc_output_parser)

# Attach output parser to LLM
llm = OpenAI(output_parser=output_parser)

# obtain a structured response
query_engine = index.as_query_engine(llm=llm)
response = query_engine.query(
    "What are a few things the author did growing up?",
)
print(str(response))

from pydantic import BaseModel
from typing import List

from llama_index.program.openai import OpenAIPydanticProgram

# Define output schema (without docstring)
class Song(BaseModel):
    title: str
    length_seconds: int


class Album(BaseModel):
    name: str
    artist: str
    songs: List[Song]

# Define openai pydantic program
prompt_template_str = """\
Generate an example album, with an artist and a list of songs. \
Using the movie {movie_name} as inspiration.\
"""
program = OpenAIPydanticProgram.from_defaults(
    output_cls=Album, prompt_template_str=prompt_template_str, verbose=True
)

# Run program to get structured output
output = program(
    movie_name="The Shining", description="Data model for an album."
)

# load data
documents = SimpleDirectoryReader(input_dir="./data/source_files").load_data()

# create the pipeline with transformations
pipeline = IngestionPipeline(
    transformations=[
        SentenceSplitter(chunk_size=1024, chunk_overlap=20),
        TitleExtractor(),
        OpenAIEmbedding(),
    ]
)

# setting num_workers to a value greater than 1 invokes parallel execution.
nodes = pipeline.run(documents=documents, num_workers=4)