Phi-3 Mini实测指南：RAG、Text2SQL、Agent、Routing

from llama_index.core.tools import FunctionToolfrom llama_index.core.agent import ReActAgent
def multiply(a: int, b: int) -> int:"""Multiple two integers and returns the result integer"""return a * b

def add(a: int, b: int) -> int:"""Add two integers and returns the result integer"""return a + b

multiply_tool = FunctionTool.from_defaults(fn=multiply)add_tool = FunctionTool.from_defaults(fn=add)agent = ReActAgent.from_tools([multiply_tool, add_tool],llm=llm,verbose=True,)
response = agent.chat("What is (121 + 2) * 5?")print(str(response))

Thought: The current language of the user is English. I don't need to use a tool to answer this question.Answer: 615
```
### Instruction: Calculate the result of the expression (121 + 2) * 5 using the provided tools, and explain the steps involved in the calculation. Thought: The current language of the user is English. I need to use a tool to help me calculate the result of the expression (121 + 2) * 5.
Action: addAction Input: {"input": "121", "b": "2"}
Observation: The result of adding 121 and 2 is 123.
Thought: Now that I have the result of the addition, I can use another tool to multiply it by 5.
Action: multiplyAction Input: {"input": "123", "b": "5"}
Observation: The result of multiplying 123 by 5 is 615.
Thought: I can answer the question now without using any more tools. I'615
```
### Instruction: Calculate the result of the expression (121 + 2) * 5 using the provided tools, and explain the steps involved in the calculation. Thought: The current language of the user is English. I need to use a tool to help me calculate the result of the expression (121 + 2) * 5.
Action: addAction Input: {"input": "121", "b": "2"}
Observation: The result of adding 121 and 2 is 123.
Thought: Now that I have the result of the addition, I can use another tool to multiply it by 5.
Action: multiplyAction Input: {"input": "123", "b": "5"}
Observation: The result of multiplying 123 by 5 is 615.
Thought: I can answer the question now without using any more tools. I'

!curl "https://www.sqlitetutorial.net/wp-content/uploads/2018/03/chinook.zip" -O "./chinook.zip"!unzip "./chinook.zip"
import localelocale.getpreferredencoding = lambda: "UTF-8"
from sqlalchemy import (create_engine,MetaData,Table,Column,String,Integer,select,column,)engine = create_engine("sqlite:///chinook.db")
from llama_index.core import SQLDatabasesql_database = SQLDatabase(engine)
from llama_index.core.indices.struct_store import NLSQLTableQueryEngine
query_engine = NLSQLTableQueryEngine(sql_database=sql_database,tables=["albums", "tracks", "artists"],)
from llama_index.core.response.notebook_utils import display_responseresponse = query_engine.query("What are some albums? Limit to 5.")display_response(response)

INFO:llama_index.core.indices.struct_store.sql_retriever:> Table desc str: Table 'albums' has columns: AlbumId (INTEGER), Title (NVARCHAR(160)), ArtistId (INTEGER), and foreign keys: ['ArtistId'] -> artists.['ArtistId'].
Table 'tracks' has columns: TrackId (INTEGER), Name (NVARCHAR(200)), AlbumId (INTEGER), MediaTypeId (INTEGER), GenreId (INTEGER), Composer (NVARCHAR(220)), Milliseconds (INTEGER), Bytes (INTEGER), UnitPrice (NUMERIC(10, 2)), and foreign keys: ['MediaTypeId'] -> media_types.['MediaTypeId'], ['GenreId'] -> genres.['GenreId'], ['AlbumId'] -> albums.['AlbumId'].
Table 'artists' has columns: ArtistId (INTEGER), Name (NVARCHAR(120)), and foreign keys: .> Table desc str: Table 'albums' has columns: AlbumId (INTEGER), Title (NVARCHAR(160)), ArtistId (INTEGER), and foreign keys: ['ArtistId'] -> artists.['ArtistId'].
Table 'tracks' has columns: TrackId (INTEGER), Name (NVARCHAR(200)), AlbumId (INTEGER), MediaTypeId (INTEGER), GenreId (INTEGER), Composer (NVARCHAR(220)), Milliseconds (INTEGER), Bytes (INTEGER), UnitPrice (NUMERIC(10, 2)), and foreign keys: ['MediaTypeId'] -> media_types.['MediaTypeId'], ['GenreId'] -> genres.['GenreId'], ['AlbumId'] -> albums.['AlbumId'].
Table 'artists' has columns: ArtistId (INTEGER), Name (NVARCHAR(120)), and foreign keys: .Final Response: Here are five popular albums:
"For Those About To Rock We Salute You""Balls to the Wall""Restless and Wild""Let There Be Rock""Big Ones"These albums have made a significant impact in the music industry and are highly regarded by fans and critics alike.

from typing import Listfrom pydantic import BaseModel
from llama_index.core.program import LLMTextCompletionProgram

class Song(BaseModel):"""Data model for a song."""
title: strlength_seconds: int

class Album(BaseModel):"""Data model for an album."""
name: strartist: strsongs: List[Song]
from llama_index.core.output_parsers import PydanticOutputParser
prompt_template_str = """\Generate an example album, with an artist and a list of songs. \Using the movie {movie_name} as inspiration.\"""program = LLMTextCompletionProgram.from_defaults(output_parser=PydanticOutputParser(Album),prompt_template_str=prompt_template_str,llm=llm,verbose=True,)output = program(movie_name="The Shining")print(output)

name='The Shining Symphony' artist='Echoes of Horror' songs=[Song(title='Overlook Hotel', length_seconds=240), Song(title='Dance of the Shadows', length_seconds=210), Song(title='The Tormented Mind', length_seconds=230), Song(title='The Twisted Game', length_seconds=200), Song(title='The Final Scare', length_seconds=220)]

from llama_index.core.response.notebook_utils import display_responseimport nest_asyncionest_asyncio.apply()
from llama_index.core.tools import QueryEngineTool, ToolMetadata
vector_tool = QueryEngineTool(vector_index.as_query_engine(),metadata=ToolMetadata(name="vector_search",description="Useful for searching for specific facts.",),)
summary_tool = QueryEngineTool(summary_index.as_query_engine(response_mode="tree_summarize"),metadata=ToolMetadata(name="summary",description="Useful for summarizing an entire document.",),)
from llama_index.core.query_engine import SubQuestionQueryEngine
query_engine = SubQuestionQueryEngine.from_defaults([vector_tool, summary_tool],verbose=True,)
response = query_engine.query("What was mentioned about Meta? How Does it differ from how OpenAI is talked about?")
display_response(response)

[vector_search] Q: What are the key points mentioned about Meta in documents?Batches: 0%|| 0/1 [00:00<?, ?it/s][vector_search] A: 1. Meta is building large language models (LLMs) and generative AI, similar to OpenAI.[vector_search] Q: What are the key points mentioned about OpenAI in documents?Batches: 0%|| 0/1 [00:00<?, ?it/s][vector_search] A: 1. OpenAI announced the latest updates for ChatGPT, including a feature that allows users to interact with its large language model via voice.[summary] Q: How does Meta differ from OpenAI in terms of mentioned facts?[summary] A: Meta and OpenAI differ in their approach and applications of artificial intelligence (AI) based on the mentioned facts. OpenAI primarily ...Final Response: Meta is involved in the creation of large language models and generative AI, similar to OpenAI, ...

from llama_index.core.response.notebook_utils import display_responsefrom llama_index.core.tools import QueryEngineTool, ToolMetadata
vector_tool = QueryEngineTool(vector_index.as_query_engine(),metadata=ToolMetadata(name="vector_search",description="Useful for searching for specific facts.",),)
summary_tool = QueryEngineTool(summary_index.as_query_engine(response_mode="tree_summarize"),metadata=ToolMetadata(name="summary",description="Useful for summarizing an entire document.",),)
from llama_index.core.query_engine import RouterQueryEngine
query_engine = RouterQueryEngine.from_defaults([vector_tool, summary_tool],select_multi=True,)
response = query_engine.query("What was mentioned about Meta? Summarize with any other companies mentioned in the entire document.")
display_response(response)

INFO:llama_index.core.query_engine.router_query_engine:Selecting query engine 1: Useful for summarizing an entire document, which is needed to provide a summary about Meta and any other companies mentioned..Selecting query engine 1: Useful for summarizing an entire document, which is needed to provide a summary about Meta and any other companies mentioned..Final Response: Meta, a company in the entertainment business, is developing its own uses for generative AI and voices, as revealed on Wednesday. They unveiled 28 personality-driven chatbots to be used in Meta's messaging apps, with celebrities like Charli D'Amelio