Retrieval-erweiterte Generierung (RAG) mit Milvus und Camel

Dieser Leitfaden zeigt, wie ein Retrieval-Augmented Generation (RAG) System mit CAMEL und Milvus aufgebaut werden kann.

Das RAG-System kombiniert ein Retrievalsystem mit einem generativen Modell, um neuen Text auf der Grundlage einer vorgegebenen Aufforderung zu generieren. Das System ruft zunächst relevante Dokumente aus einem Korpus mit Milvus ab und verwendet dann ein generatives Modell, um neuen Text auf der Grundlage der abgerufenen Dokumente zu erzeugen.

CAMEL ist ein Multiagentensystem. Milvus ist die weltweit fortschrittlichste Open-Source-Vektordatenbank, die für die Einbettung von Ähnlichkeitssuche und KI-Anwendungen entwickelt wurde.

In diesem Notizbuch zeigen wir die Verwendung des CAMEL Retrieve Moduls sowohl auf angepasste als auch auf automatische Weise. Wir zeigen auch, wie man AutoRetriever mit ChatAgent und AutoRetriever mit RolePlaying unter Verwendung von Function Calling kombiniert.

4 Hauptteile enthalten:

• Angepasste RAG
• Automatische RAG
• Einzelagent mit Auto RAG
• Rollenspiele mit Auto RAG

Daten laden

Laden wir zunächst das CAMEL-Papier von https://arxiv.org/pdf/2303.17760.pdf. Dies werden unsere lokalen Beispieldaten sein.

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

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. Angepasste RAG

In diesem Abschnitt werden wir unsere benutzerdefinierte RAG-Pipeline einrichten. Wir nehmen VectorRetriever als Beispiel. Wir werden OpenAIEmbedding als Einbettungsmodell und MilvusStorage als Speicherort dafür festlegen.

Um die OpenAI-Einbettung einzustellen, müssen wir die OPENAI_API_KEY im Folgenden einstellen.

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

Importieren und setzen Sie die Einbettungsinstanz:

from camel.embeddings import OpenAIEmbedding

embedding_instance = OpenAIEmbedding()

Importieren und Einstellen der Vektorspeicherinstanz:

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",
)

Importieren und setzen Sie die Retriever-Instanz:

Standardmäßig ist die similarity_threshold auf 0,75 eingestellt. Sie können ihn ändern.

from camel.retrievers import VectorRetriever

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

Wir verwenden die integrierte Funktion Unstructured Module, um den Inhalt in kleine Chunks aufzuteilen. Der Inhalt wird automatisch mit der Funktion chunk_by_title aufgeteilt, die maximale Zeichenlänge für jeden Chunk beträgt 500 Zeichen, was eine geeignete Länge für OpenAIEmbedding ist. Der gesamte Text in den Chunks wird eingebettet und in der Vektor-Speicherinstanz gespeichert, was einige Zeit in Anspruch nehmen wird.

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.

Nun können wir Informationen aus dem Vektorspeicher abrufen, indem wir eine Abfrage stellen. Standardmäßig wird der Textinhalt des ersten Chunks mit der höchsten Cosinus-Ähnlichkeitsbewertung zurückgegeben, und die Ähnlichkeitsbewertung sollte höher als 0,75 sein, um sicherzustellen, dass der abgerufene Inhalt für die Abfrage relevant ist. Sie können auch den Wert top_k ändern.

Die zurückgegebene String-Liste enthält:

• Ähnlichkeitsgrad
• Inhaltspfad
• Metadaten
• Text

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'}]

Versuchen wir es mit einer irrelevanten Abfrage:

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. Auto RAG

In diesem Abschnitt wird AutoRetriever mit den Standardeinstellungen ausgeführt. Es verwendet OpenAIEmbedding als Standard-Einbettungsmodell und Milvus als Standard-Vektorspeicher.

Was Sie tun müssen, ist:

• Eingabepfade für den Inhalt festlegen, die lokale Pfade oder entfernte URLs sein können
• Remote-Url und API-Schlüssel für Milvus festlegen
• Geben Sie eine Abfrage ein

Die Auto-RAG-Pipeline erstellt Sammlungen für gegebene Inhaltseingabepfade, der Sammlungsname wird automatisch auf der Grundlage des Inhaltseingabepfads festgelegt, wenn die Sammlung existiert, wird sie direkt abgerufen.

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. Einzelagent mit Auto RAG

In diesem Abschnitt zeigen wir, wie man AutoRetriever mit einem ChatAgent kombiniert.

Legen wir eine Agentenfunktion fest, in dieser Funktion können wir die Antwort erhalten, indem wir eine Abfrage an diesen Agenten stellen.

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. Rollenspiele mit Auto RAG

In diesem Abschnitt werden wir zeigen, wie man RETRIEVAL_FUNCS mit RolePlaying kombiniert, indem man Function Calling anwendet.

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

Führen Sie das Rollenspiel mit der definierten Retriever-Funktion aus:

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.