Multi-agent Systems With AutoGen and MongoDB

1
    conda create -n pyautogen python=3.12
2
    conda activate pyautogen

1
!pip install pyautogen pymongo sentence_transformers

1
!pip install ipython markdownify pypdf chromadb

1
import os
2
import getpass
3
4
os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
5
os.environ["MONGODB_URI"] = getpass.getpass("MongoDB URI:")

1
import json
2
import os
3
4
import autogen
5
from autogen.agentchat.contrib.retrieve_assistant_agent import RetrieveAssistantAgent
6
from autogen.agentchat.contrib.retrieve_user_proxy_agent import RetrieveUserProxyAgent
7
8
# Accepted file formats for that can be stored in
9
# a vector database instance
10
from autogen.retrieve_utils import TEXT_FORMATS
11
12
config_list = [{"model": "gpt-3.5-turbo-0125", "api_key": os.environ["OPENAI_API_KEY"], "api_type": "openai"}]
13
assert len(config_list) > 0
14
print("models to use: ", [config_list[i]["model"] for i in range(len(config_list))])
15
MONGODB_URI = os.environ["MONGODB_URI"]
16
17
print("Accepted file formats for `docs_path`:")
18
print(TEXT_FORMATS)

1
assistant = RetrieveAssistantAgent(
2
    name="assistant",
3
    system_message="You are a helpful assistant.",
4
    llm_config={
5
        "timeout": 600,
6
        "cache_seed": 42,
7
        "config_list": config_list,
8
    },
9
)

1
ragproxyagent = RetrieveUserProxyAgent(
2
    name="MongoRAGagent",
3
    human_input_mode="NEVER",
4
    max_consecutive_auto_reply=3,
5
    retrieve_config={
6
        "task": "code",
7
        "docs_path": [
8
            "https://github.com/mongodb-partners/maap-framework/blob/main/README.md",
9
            os.path.join(os.path.abspath(""), "..", "website", "docs"),
10
        ],
11
        "custom_text_types": ["non-existent-type"],
12
        "chunk_token_size": 2000,
13
        "model": config_list[0]["model"],
14
        "vector_db": "mongodb",  # MongoDB Atlas database
15
        "collection_name": "demo_collection",
16
        "db_config": {
17
            "connection_string": os.environ["MONGODB_URI"],  # MongoDB Atlas connection string
18
            "database_name": "test_db",  # MongoDB Atlas database
19
            "index_name": "vector_index",
20
            "wait_until_index_ready": 120.0,  # Setting to wait 120 seconds or until index is constructed before querying
21
            "wait_until_document_ready": 120.0,  # Setting to wait 120 seconds or until document is properly indexed after insertion/update
22
        },
23
        "get_or_create": True,  # set to False if you don't want to reuse an existing collection
24
        "overwrite": False,  # set to True if you want to overwrite an existing collection, each overwrite will force a index creation and reupload of documents
25
    },
26
    code_execution_config=False,  # set to False if you don't want to execute the code
27
)

1
assistant.reset()
2
3
code_problem = "How does the MAAP framework handle data ingestion?"
4
chat_result = ragproxyagent.initiate_chat(assistant, message=ragproxyagent.message_generator, problem=code_problem)

1
--------------------------------------------------------------------------------
2
assistant (to MongoRAGagent):
3
4
The MAAP framework handles data ingestion by providing support for multiple types of data loaders tailored to handle specific data sources such as web pages, PDF files, sitemaps, DOCX documents, and Confluence spaces. These data loaders are configured with parameters like source paths and chunking details and are added to a data loaders array for processing. The process of ingesting data involves configuring the application, running the server, and starting the UI client application to interact with the data through a web interface.
5
6
--------------------------------------------------------------------------------