milvus-logo
LFAI
Casa
  • Integrazioni
    • Agenti

Generazione Aumentata del Recupero (RAG) con Milvus e Camel

Open In Colab GitHub Repository

Questa guida mostra come costruire un sistema di Retrieval-Augmented Generation (RAG) utilizzando CAMEL e Milvus.

Il sistema RAG combina un sistema di recupero con un modello generativo per generare nuovo testo in base a un prompt dato. Il sistema recupera prima i documenti rilevanti da un corpus utilizzando Milvus e poi utilizza un modello generativo per generare nuovo testo sulla base dei documenti recuperati.

CAMEL è un framework multi-agente. Milvus è il database vettoriale open-source più avanzato al mondo, costruito per alimentare la ricerca di similarità di incorporamento e le applicazioni di intelligenza artificiale.

In questo quaderno, mostriamo l'uso del modulo CAMEL Retrieve sia in modo personalizzato che automatico. Mostreremo anche come combinare AutoRetriever con ChatAgent, e come combinare ulteriormente AutoRetriever con RolePlaying usando Function Calling.

Sono incluse 4 parti principali:

  • RAG personalizzato
  • RAG automatico
  • Agente singolo con Auto RAG
  • Gioco di ruolo con Auto RAG

Caricare i dati

Carichiamo innanzitutto il documento CAMEL da https://arxiv.org/pdf/2303.17760.pdf. Questi saranno i nostri dati di esempio locali.

$ pip install -U "camel-ai[all]" pymilvus

Se si utilizza Google Colab, per abilitare le dipendenze appena installate, potrebbe essere necessario riavviare il runtime (fare clic sul menu "Runtime" nella parte superiore dello schermo e selezionare "Restart session" dal menu a discesa).

import os
import requests

os.makedirs("local_data", exist_ok=True)

url = "https://arxiv.org/pdf/2303.17760.pdf"
response = requests.get(url)
with open("local_data/camel paper.pdf", "wb") as file:
    file.write(response.content)

1. RAG personalizzato

In questa sezione imposteremo la nostra pipeline RAG personalizzata; prenderemo come esempio VectorRetriever. Impostiamo OpenAIEmbedding come modello di embedding e MilvusStorage come archivio.

Per impostare l'embedding di OpenAI, dobbiamo impostare OPENAI_API_KEY come segue.

os.environ["OPENAI_API_KEY"] = "Your Key"

Importare e impostare l'istanza di embedding:

from camel.embeddings import OpenAIEmbedding

embedding_instance = OpenAIEmbedding()

Importare e impostare l'istanza di memorizzazione vettoriale:

from camel.storages import MilvusStorage

storage_instance = MilvusStorage(
    vector_dim=embedding_instance.get_output_dim(),
    url_and_api_key=(
        "./milvus_demo.db",  # Your Milvus connection URI
        "",  # Your Milvus token
    ),
    collection_name="camel_paper",
)

Per url_and_api_key:

  • L'utilizzo di un file locale, ad esempio./milvus.db, come URI di connessione a Milvus è il metodo più conveniente, poiché utilizza automaticamente Milvus Lite per memorizzare tutti i dati in questo file.
  • Se si dispone di una grande quantità di dati, è possibile configurare un server Milvus più performante su docker o kubernetes. In questa configurazione, utilizzare l'uri del server, ad esempiohttp://localhost:19530, come url.
  • Se si desidera utilizzare Zilliz Cloud, il servizio cloud completamente gestito per Milvus, regolare l'uri e il token di connessione, che corrispondono all'endpoint pubblico e alla chiave Api di Zilliz Cloud.

Importare e impostare l'istanza del retriever:

Per impostazione predefinita, similarity_threshold è impostato su 0,75. È possibile modificarlo.

from camel.retrievers import VectorRetriever

vector_retriever = VectorRetriever(
    embedding_model=embedding_instance, storage=storage_instance
)

Utilizziamo Unstructured Module integrato per suddividere il contenuto in piccoli pezzi, il contenuto sarà suddiviso automaticamente con la funzione chunk_by_title, il carattere massimo per ogni pezzo è di 500 caratteri, che è una lunghezza adatta per OpenAIEmbedding. Tutto il testo contenuto nei pezzi verrà incorporato e memorizzato nell'istanza di archiviazione vettoriale; ci vorrà un po' di tempo, si prega di attendere.

vector_retriever.process(content_input_path="local_data/camel paper.pdf")
[nltk_data] Downloading package punkt to /root/nltk_data...
[nltk_data]   Unzipping tokenizers/punkt.zip.
[nltk_data] Downloading package averaged_perceptron_tagger to
[nltk_data]     /root/nltk_data...
[nltk_data]   Unzipping taggers/averaged_perceptron_tagger.zip.

Ora possiamo recuperare le informazioni dal magazzino vettoriale fornendo una query. Per impostazione predefinita, verranno restituiti i contenuti testuali dei primi 1 chunk con il punteggio di somiglianza Cosine più alto; il punteggio di somiglianza deve essere superiore a 0,75 per garantire che i contenuti recuperati siano pertinenti alla query. È possibile modificare il valore di top_k.

L'elenco delle stringhe restituite include:

  • punteggio di somiglianza
  • percorso del contenuto
  • metadati
  • testo
retrieved_info = vector_retriever.query(query="What is CAMEL?", top_k=1)
print(retrieved_info)
[{'similarity score': '0.8321675658226013', 'content path': 'local_data/camel paper.pdf', 'metadata': {'last_modified': '2024-04-19T14:40:00', 'filetype': 'application/pdf', 'page_number': 45}, 'text': 'CAMEL Data and Code License The intended purpose and licensing of CAMEL is solely for research use. The source code is licensed under Apache 2.0. The datasets are licensed under CC BY NC 4.0, which permits only non-commercial usage. It is advised that any models trained using the dataset should not be utilized for anything other than research purposes.\n\n45'}]

Proviamo a fare una query non pertinente:

retrieved_info_irrelevant = vector_retriever.query(
    query="Compared with dumpling and rice, which should I take for dinner?", top_k=1
)

print(retrieved_info_irrelevant)
[{'text': 'No suitable information retrieved from local_data/camel paper.pdf                 with similarity_threshold = 0.75.'}]

2. RAG automatico

In questa sezione verrà eseguito AutoRetriever con le impostazioni predefinite. Utilizza OpenAIEmbedding come modello di incorporamento predefinito e Milvus come memorizzazione vettoriale predefinita.

Le operazioni da eseguire sono le seguenti:

  • Impostare i percorsi di input del contenuto, che possono essere percorsi locali o URL remoti.
  • Impostare l'url remoto e la chiave api per Milvus
  • Fornire una query

La pipeline Auto RAG creerà collezioni per i percorsi di input del contenuto dati, il nome della collezione sarà impostato automaticamente in base al nome del percorso di input del contenuto, se la collezione esiste, effettuerà direttamente il recupero.

from camel.retrievers import AutoRetriever
from camel.types import StorageType

auto_retriever = AutoRetriever(
    url_and_api_key=(
        "./milvus_demo.db",  # Your Milvus connection URI
        "",  # Your Milvus token
    ),
    storage_type=StorageType.MILVUS,
    embedding_model=embedding_instance,
)

retrieved_info = auto_retriever.run_vector_retriever(
    query="What is CAMEL-AI",
    content_input_paths=[
        "local_data/camel paper.pdf",  # example local path
        "https://www.camel-ai.org/",  # example remote url
    ],
    top_k=1,
    return_detailed_info=True,
)

print(retrieved_info)
Original Query:
{What is CAMEL-AI}
Retrieved Context:
{'similarity score': '0.8252888321876526', 'content path': 'local_data/camel paper.pdf', 'metadata': {'last_modified': '2024-04-19T14:40:00', 'filetype': 'application/pdf', 'page_number': 7}, 'text': ' Section 3.2, to simulate assistant-user cooperation. For our analysis, we set our attention on AI Society setting. We also gathered conversational data, named CAMEL AI Society and CAMEL Code datasets and problem-solution pairs data named CAMEL Math and CAMEL Science and analyzed and evaluated their quality. Moreover, we will discuss potential extensions of our framework and highlight both the risks and opportunities that future AI society might present.'}
{'similarity score': '0.8378663659095764', 'content path': 'https://www.camel-ai.org/', 'metadata': {'filetype': 'text/html', 'languages': ['eng'], 'page_number': 1, 'url': 'https://www.camel-ai.org/', 'link_urls': ['#h.3f4tphhd9pn8', 'https://join.slack.com/t/camel-ai/shared_invite/zt-2g7xc41gy-_7rcrNNAArIP6sLQqldkqQ', 'https://discord.gg/CNcNpquyDc'], 'link_texts': [None, None, None], 'emphasized_text_contents': ['Mission', 'CAMEL-AI.org', 'is an open-source community dedicated to the study of autonomous and communicative agents. We believe that studying these agents on a large scale offers valuable insights into their behaviors, capabilities, and potential risks. To facilitate research in this field, we provide, implement, and support various types of agents, tasks, prompts, models, datasets, and simulated environments.', 'Join us via', 'Slack', 'Discord', 'or'], 'emphasized_text_tags': ['span', 'span', 'span', 'span', 'span', 'span', 'span']}, 'text': 'Mission\n\nCAMEL-AI.org is an open-source community dedicated to the study of autonomous and communicative agents. We believe that studying these agents on a large scale offers valuable insights into their behaviors, capabilities, and potential risks. To facilitate research in this field, we provide, implement, and support various types of agents, tasks, prompts, models, datasets, and simulated environments.\n\nJoin us via\n\nSlack\n\nDiscord\n\nor'}

3. Agente singolo con RAG automatico

In questa sezione mostreremo come combinare il sito AutoRetriever con un unico ChatAgent.

Impostiamo una funzione agente, in questa funzione possiamo ottenere la risposta fornendo una query a questo agente.

from camel.agents import ChatAgent
from camel.messages import BaseMessage
from camel.types import RoleType
from camel.retrievers import AutoRetriever
from camel.types import StorageType


def single_agent(query: str) -> str:
    # Set agent role
    assistant_sys_msg = BaseMessage(
        role_name="Assistant",
        role_type=RoleType.ASSISTANT,
        meta_dict=None,
        content="""You are a helpful assistant to answer question,
         I will give you the Original Query and Retrieved Context,
        answer the Original Query based on the Retrieved Context,
        if you can't answer the question just say I don't know.""",
    )

    # Add auto retriever
    auto_retriever = AutoRetriever(
        url_and_api_key=(
            "./milvus_demo.db",  # Your Milvus connection URI
            "",  # Your Milvus token
        ),
        storage_type=StorageType.MILVUS,
        embedding_model=embedding_instance,
    )

    retrieved_info = auto_retriever.run_vector_retriever(
        query=query,
        content_input_paths=[
            "local_data/camel paper.pdf",  # example local path
            "https://www.camel-ai.org/",  # example remote url
        ],
        # vector_storage_local_path="storage_default_run",
        top_k=1,
        return_detailed_info=True,
    )

    # Pass the retrieved infomation to agent
    user_msg = BaseMessage.make_user_message(role_name="User", content=retrieved_info)
    agent = ChatAgent(assistant_sys_msg)

    # Get response
    assistant_response = agent.step(user_msg)
    return assistant_response.msg.content


print(single_agent("What is CAMEL-AI"))
CAMEL-AI is an open-source community dedicated to the study of autonomous and communicative agents. It provides, implements, and supports various types of agents, tasks, prompts, models, datasets, and simulated environments to facilitate research in this field.

4. Gioco di ruolo con Auto RAG

In questa sezione mostreremo come combinare RETRIEVAL_FUNCS con RolePlaying applicando Function Calling.

from typing import List
from colorama import Fore

from camel.agents.chat_agent import FunctionCallingRecord
from camel.configs import ChatGPTConfig
from camel.functions import (
    MATH_FUNCS,
    RETRIEVAL_FUNCS,
)
from camel.societies import RolePlaying
from camel.types import ModelType
from camel.utils import print_text_animated


def role_playing_with_rag(
    task_prompt, model_type=ModelType.GPT_4O, chat_turn_limit=10
) -> None:
    task_prompt = task_prompt

    user_model_config = ChatGPTConfig(temperature=0.0)

    function_list = [
        *MATH_FUNCS,
        *RETRIEVAL_FUNCS,
    ]
    assistant_model_config = ChatGPTConfig(
        tools=function_list,
        temperature=0.0,
    )

    role_play_session = RolePlaying(
        assistant_role_name="Searcher",
        user_role_name="Professor",
        assistant_agent_kwargs=dict(
            model_type=model_type,
            model_config=assistant_model_config,
            tools=function_list,
        ),
        user_agent_kwargs=dict(
            model_type=model_type,
            model_config=user_model_config,
        ),
        task_prompt=task_prompt,
        with_task_specify=False,
    )

    print(
        Fore.GREEN
        + f"AI Assistant sys message:\n{role_play_session.assistant_sys_msg}\n"
    )
    print(Fore.BLUE + f"AI User sys message:\n{role_play_session.user_sys_msg}\n")

    print(Fore.YELLOW + f"Original task prompt:\n{task_prompt}\n")
    print(
        Fore.CYAN
        + f"Specified task prompt:\n{role_play_session.specified_task_prompt}\n"
    )
    print(Fore.RED + f"Final task prompt:\n{role_play_session.task_prompt}\n")

    n = 0
    input_msg = role_play_session.init_chat()
    while n < chat_turn_limit:
        n += 1
        assistant_response, user_response = role_play_session.step(input_msg)

        if assistant_response.terminated:
            print(
                Fore.GREEN
                + (
                    "AI Assistant terminated. Reason: "
                    f"{assistant_response.info['termination_reasons']}."
                )
            )
            break
        if user_response.terminated:
            print(
                Fore.GREEN
                + (
                    "AI User terminated. "
                    f"Reason: {user_response.info['termination_reasons']}."
                )
            )
            break

        # Print output from the user
        print_text_animated(Fore.BLUE + f"AI User:\n\n{user_response.msg.content}\n")

        # Print output from the assistant, including any function
        # execution information
        print_text_animated(Fore.GREEN + "AI Assistant:")
        tool_calls: List[FunctionCallingRecord] = assistant_response.info["tool_calls"]
        for func_record in tool_calls:
            print_text_animated(f"{func_record}")
        print_text_animated(f"{assistant_response.msg.content}\n")

        if "CAMEL_TASK_DONE" in user_response.msg.content:
            break

        input_msg = assistant_response.msg

Eseguire il gioco di ruolo con la funzione retriever definita:

role_playing_with_rag(
    task_prompt="""What is the main termination reasons for AI Society
                   dataset, how many number of messages did camel decided to
                   limit, what's the value plus 100? You should refer to the
                   content in path camel/local_data/camel paper.pdf"""
)
AI Assistant sys message:
BaseMessage(role_name='Searcher', role_type=<RoleType.ASSISTANT: 'assistant'>, meta_dict={'task': "What is the main termination reasons for AI Society dataset, how many number of messages did camel decided to limit, what's the value plus 100?", 'assistant_role': 'Searcher', 'user_role': 'Professor'}, content="===== RULES OF ASSISTANT =====\nNever forget you are a Searcher and I am a Professor. Never flip roles! Never instruct me!\nWe share a common interest in collaborating to successfully complete a task.\nYou must help me to complete the task.\nHere is the task: What is the main termination reasons for AI Society dataset, how many number of messages did camel decided to limit, what's the value plus 100?. Never forget our task!\nI must instruct you based on your expertise and my needs to complete the task.\n\nI must give you one instruction at a time.\nYou must write a specific solution that appropriately solves the requested instruction and explain your solutions.\nYou must decline my instruction honestly if you cannot perform the instruction due to physical, moral, legal reasons or your capability and explain the reasons.\nUnless I say the task is completed, you should always start with:\n\nSolution: <YOUR_SOLUTION>\n\n<YOUR_SOLUTION> should be very specific, include detailed explanations and provide preferable detailed implementations and examples and lists for task-solving.\nAlways end <YOUR_SOLUTION> with: Next request.")

AI User sys message:
BaseMessage(role_name='Professor', role_type=<RoleType.USER: 'user'>, meta_dict={'task': "What is the main termination reasons for AI Society dataset, how many number of messages did camel decided to limit, what's the value plus 100?", 'assistant_role': 'Searcher', 'user_role': 'Professor'}, content='===== RULES OF USER =====\nNever forget you are a Professor and I am a Searcher. Never flip roles! You will always instruct me.\nWe share a common interest in collaborating to successfully complete a task.\nI must help you to complete the task.\nHere is the task: What is the main termination reasons for AI Society dataset, how many number of messages did camel decided to limit, what\'s the value plus 100?. Never forget our task!\nYou must instruct me based on my expertise and your needs to solve the task ONLY in the following two ways:\n\n1. Instruct with a necessary input:\nInstruction: <YOUR_INSTRUCTION>\nInput: <YOUR_INPUT>\n\n2. Instruct without any input:\nInstruction: <YOUR_INSTRUCTION>\nInput: None\n\nThe "Instruction" describes a task or question. The paired "Input" provides further context or information for the requested "Instruction".\n\nYou must give me one instruction at a time.\nI must write a response that appropriately solves the requested instruction.\nI must decline your instruction honestly if I cannot perform the instruction due to physical, moral, legal reasons or my capability and explain the reasons.\nYou should instruct me not ask me questions.\nNow you must start to instruct me using the two ways described above.\nDo not add anything else other than your instruction and the optional corresponding input!\nKeep giving me instructions and necessary inputs until you think the task is completed.\nWhen the task is completed, you must only reply with a single word <CAMEL_TASK_DONE>.\nNever say <CAMEL_TASK_DONE> unless my responses have solved your task.')

Original task prompt:
What is the main termination reasons for AI Society dataset, how many number of messages did camel decided to limit, what's the value plus 100?

Specified task prompt:
None

Final task prompt:
What is the main termination reasons for AI Society dataset, how many number of messages did camel decided to limit, what's the value plus 100?



AI User:

Instruction: Provide a summary of the main termination reasons in the AI Society dataset.
Input: None


AI Assistant:

Function Execution: local_retriever
    Args: {'query': 'main termination reasons for AI Society dataset'}
    Result: Original Query:
{main termination reasons for AI Society dataset}
Retrieved Context:
Next we examine the conversation termination reasons for both AI Society and Code datasets. As can be seen in Figure 8, the main termination reasons for AI Society dataset is Assistant Instruct whereas for Code it is Token Limit. The latter is expected as the since responses that contain code tend to be long. It is also interesting to note that in both datasets, the termination due to Maximum Number of Messages is low indicating that the limit of 40 maximum messages is reasonable. Our decision t

Solution: The main termination reason for the AI Society dataset is "Assistant Instruct." This indicates that conversations in the AI Society dataset typically end when the assistant is instructed to terminate the conversation.

Next request.


AI User:

Instruction: Identify the number of messages that the camel decided to limit in the context provided.
Input: None


AI Assistant:

Solution: The context provided from the local retriever indicates that the camel decided to limit the number of messages to a maximum of 40 messages. This is mentioned in the retrieved context where it states that the termination due to Maximum Number of Messages is low, indicating that the limit of 40 maximum messages is reasonable.

Next request.


AI User:

Instruction: Calculate the value of the message limit plus 100.
Input: None


AI Assistant:

Function Execution: add
    Args: {'a': 40, 'b': 100}
    Result: 140

Solution: The value of the message limit plus 100 is 140.

Next request.


AI User:

CAMEL_TASK_DONE


AI Assistant:

Solution: Understood, the task is completed.

Next request.

Tradotto daDeepLogo

Try Managed Milvus for Free

Zilliz Cloud is hassle-free, powered by Milvus and 10x faster.

Get Started
Feedback

Questa pagina è stata utile?