# 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, }
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?", )
另外，通过各种嵌入技术和排序器，我们可以对检索性能进行评估和提升，详见 提升 RAG 性能：挑选最优的嵌入技术和排序模型* 由 Ravi Theja 撰写。
更进一步，定制化的排序器经过微调后能够实现更优的检索性能，具体实施方法请参阅 通过微调 Cohere 排序器与 LlamaIndex 提升检索效果*，也是由 Ravi Theja 介绍。
from llama_index.query_engine import RetrieverQueryEngine from llama_index.response_synthesizers import CompactAndRefine from llama_index.postprocessor import LongLLMLinguaPostprocessor from llama_index.schema 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 }, )
from llama_index import VectorStoreIndex, SimpleDirectoryReader from llama_index.output_parsers import LangchainOutputParser from llama_index.llms 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.", ), ]
## Attach output parser to LLM llm = OpenAI(output_parser=output_parser)
## obtain a structured response from llama_index import ServiceContext
ctx = ServiceContext.from_defaults(llm=llm)
query_engine = index.as_query_engine(service_context=ctx) 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 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 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)
基于 Wang 等人创新的“链式表格”论文，ChainOfTablePack 是一种特别设计的工具包。这种方法通过“链式思维”与表格的转换及展示相结合，允许以一套限定的操作逐步变化表格，并在每一步中将变化后的表格展示给大语言模型。这种方式特别适合处理包含多重信息的复杂表格单元问题，通过逐步精确地切割和解析数据，直至找到所需的数据子集，显著提高了对表格数据的查询效率。欲了解如何利用 ChainOfTablePack 来优化您的结构化数据查询，详见 LlamaIndex 提供的实践指南。
2.混合自洽查询引擎包
大语言模型（LLM）能以两种主要方式对表格数据进行推理：
通过直接询问进行文本推理
通过程序合成（如 Python、SQL 等）进行符号推理
依据 Liu 等人的研究《重新思考大语言模型如何理解表格数据》，LlamaIndex 创新性地开发了 MixSelfConsistencyQueryEngine。该引擎结合了文本与符号推理的结果，并通过自洽机制（即，多数投票法）实现了最先进（State of the Art，SoTA）的性能表现。以下是一个示例代码片段。欲了解更多细节，可以查阅 LlamaIndex 的完整笔记本。
在从复杂 PDF 文档，如嵌入表格的文档中提取数据进行问答时，传统的检索方法往往无法达到目的。您需要一个更高效的方法来处理这种复杂的 PDF 数据提取需求。
1.嵌入式表格检索技术
LlamaIndex 提出了一种解决方案，名为 EmbeddedTablesUnstructuredRetrieverPack。这个 LlamaPack 利用 Unstructured.io 解析 HTML 文档中的嵌入式表格，创建节点图，并通过递归检索根据用户提出的问题来索引和检索表格。
请注意，此方案需要将 PDF 文档作为输入。如果您手头上的是 PDF 文件，可以使用 pdf2htmlEX 工具，将 PDF 转换为 HTML 格式，同时保留原文的文字和格式。以下是如何下载、初始化及运行 EmbeddedTablesUnstructuredRetrieverPack 的示例代码片段。
## 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}"))
LlamaIndex 已经通过其llms模块中的Neutrino类，加入了对 Neutrino 的支持。详细信息请参见以下代码示例，更多细节可查阅Neutrino AI 页面。
from llama_index.llms import Neutrino from llama_index.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']}")
2.OpenRouter
OpenRouter提供了一个一站式的 API 接口，使你能够接入任何大语言模型。它不仅能帮你找到市场上任一模型的最低价格，还能在你首选的服务提供商遇到问题时，自动切换到其他选项。按照OpenRouter 的官方文档所述，选择 OpenRouter 的主要优势包括：
## 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)
实现辅助功能 moderate_and_query 的代码如下：
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.'
粤ICP备14082021号
免费POC，
零成本试错
