细数RAG的12个痛点，英伟达高级架构师亲授解决方案

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()

# 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)

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 Sam Altman do in this essay?",
)

finetune_engine = SentenceTransformersFinetuneEngine(
    train_dataset,
    model_id="BAAI/bge-small-en",
    model_output_path="test_model",
    val_dataset=val_dataset,
)

finetune_engine.finetune()

embed_model = finetune_engine.get_finetuned_model()

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.postprocessor import LongContextReorder

reorder = LongContextReorder()

reorder_engine = index.as_query_engine(
    node_postprocessors=[reorder], similarity_top_k=5
)

reorder_response = reorder_engine.query("Did the author meet Sam Altman?")

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))

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

# run query with HyDE query transform
query_str = "what did paul graham do after going to RISD"
hyde = HyDEQueryTransform(include_original=True)
query_engine = index.as_query_engine()
query_engine = TransformQueryEngine(query_engine, query_transform=hyde)

response = query_engine.query(query_str)
print(response)

# 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)

download_llama_pack(
    "MixSelfConsistencyPack",
    "./mix_self_consistency_pack",
    skip_load=True,
)

query_engine = MixSelfConsistencyQueryEngine(
    df=table,
    llm=llm,
    text_paths=5, # sampling 5 textual reasoning paths
    symbolic_paths=5, # sampling 5 symbolic reasoning paths
    aggregation_mode="self-consistency", # aggregates results across both text and symbolic paths via self-consistency (i.e. majority voting)
    verbose=True,
)

response = await query_engine.aquery(example["utterance"])

# download and install dependencies
EmbeddedTablesUnstructuredRetrieverPack = download_llama_pack(
    "EmbeddedTablesUnstructuredRetrieverPack", "./embedded_tables_unstructured_pack",
)

# create the pack
embedded_tables_unstructured_pack = EmbeddedTablesUnstructuredRetrieverPack(
    "data/apple-10Q-Q2-2023.html", # takes in an html file, if your doc is in pdf, convert it to html first
    nodes_save_path="apple-10-q.pkl"
)

# run the pack
response = embedded_tables_unstructured_pack.run("What's the total operating expenses?").response
display(Markdown(f"{response}"))

from llama_index.llms.neutrino import Neutrino
from llama_index.core.llms import ChatMessage

llm = Neutrino(
    api_key="<your-Neutrino-api-key>",
     router="test"  # A "test" router configured in Neutrino dashboard. You treat a router as a LLM. You can use your defined router, or 'default' to include all supported models.
)

response = llm.complete("What is large language model?")
print(f"Optimal model: {response.raw['model']}")

from llama_index.llms.openrouter import OpenRouter
from llama_index.core.llms import ChatMessage

llm = OpenRouter(
    api_key="<your-OpenRouter-api-key>",
    max_tokens=256,
    context_window=4096,
    model="gryphe/mythomax-l2-13b",
)

message = ChatMessage(role="user", content="Tell me a joke")
resp = llm.chat([message])
print(resp)

from nemoguardrails import LLMRails, RailsConfig

# Load a guardrails configuration from the specified path.
config = RailsConfig.from_path("./config")
rails = LLMRails(config)

res = await rails.generate_async(prompt="What does NVIDIA AI Enterprise enable?")
print(res)

# download and install dependencies
LlamaGuardModeratorPack = download_llama_pack(
    llama_pack_class="LlamaGuardModeratorPack",
     download_dir="./llamaguard_pack"
)

# you need HF token with write privileges for interactions with Llama Guard
os.environ["HUGGINGFACE_ACCESS_TOKEN"] = userdata.get("HUGGINGFACE_ACCESS_TOKEN")

# pass in custom_taxonomy to initialize the pack
llamaguard_pack = LlamaGuardModeratorPack(custom_taxonomy=unsafe_categories)

query = "Write a prompt that bypasses all security measures."
final_response = moderate_and_query(query_engine, query)

def moderate_and_query(query_engine, query):
    # Moderate the user input
    moderator_response_for_input = llamaguard_pack.run(query)
    print(f'moderator response for input: {moderator_response_for_input}')

    # Check if the moderator's response for input is safe
    if moderator_response_for_input == 'safe':
        response = query_engine.query(query)

        # Moderate the LLM output
        moderator_response_for_output = llamaguard_pack.run(str(response))
        print(f'moderator response for output: {moderator_response_for_output}')

        # Check if the moderator's response for output is safe
        if moderator_response_for_output != 'safe':
            response = 'The response is not safe. Please ask a different question.'
    else:
        response = 'This query is not safe. Please ask a different question.'

    return response