MongoDB how to setup uri if I run mongodb via Docker?

[mraguth]

I am running mongodb via docker (not via cloud setup). Is it possible to setup uri with my local docker mongodb instance?

https://docs.llamaindex.ai/en/stable/examples/vector_stores/MongoDBAtlasVectorSearch/?h=mongo_uri

# mongo_uri = os.environ["MONGO_URI"]
mongo_uri = (
    "mongodb+srv://<username>:<password>@<host>?retryWrites=true&w=majority"
)
mongodb_client = pymongo.MongoClient(mongo_uri)
store = MongoDBAtlasVectorSearch(mongodb_client)
storage_context = StorageContext.from_defaults(vector_store=store)
uber_docs = SimpleDirectoryReader(
    input_files=["./data/10k/uber_2021.pdf"]
).load_data()
index = VectorStoreIndex.from_documents(
    uber_docs, storage_context=storage_context
)

[dosubot[bot]]

To set up the URI for your local Docker MongoDB instance, you need to modify the MONGODB_URI environment variable to point to your local Docker MongoDB instance instead of a cloud setup.

Assuming your local Docker MongoDB instance is running on the default port 27017, your MONGODB_URI would look something like this:

export MONGODB_URI="mongodb://localhost:27017"

You can then use this URI in your Python code to connect to your local MongoDB instance:

from pymongo.mongo_client import MongoClient

uri = "mongodb://localhost:27017"
client = MongoClient(uri)  # Create a new client and connect to the server
try:
    client.admin.command("ping")  # Send a ping to confirm a successful connection
    print("Pinged your deployment. You successfully connected to MongoDB!")
except Exception as e:
    print(e)

In the context of using MongoDBAtlasVectorSearch with LlamaIndex, you can set up the MongoDB client and vector store as follows:

from pymongo.mongo_client import MongoClient
from llama_index.vector_stores.mongodb import MongoDBAtlasVectorSearch
from llama_index.storage import StorageContext
from llama_index.readers import SimpleDirectoryReader
from llama_index.indices import VectorStoreIndex

# Set up the MongoDB URI for your local Docker instance
mongo_uri = "mongodb://localhost:27017"
mongodb_client = MongoClient(mongo_uri)

# Create the MongoDBAtlasVectorSearch store
store = MongoDBAtlasVectorSearch(mongodb_client)

# Create the storage context
storage_context = StorageContext.from_defaults(vector_store=store)

# Read documents from a directory
uber_docs = SimpleDirectoryReader(input_files=["./data/10k/uber_2021.pdf"]).load_data()

# Create a vector store index
index = VectorStoreIndex.from_documents(uber_docs, storage_context=storage_context)

Make sure to replace localhost and 27017 with the appropriate hostname and port if your Docker MongoDB instance is configured differently ^[1].

To continue talking to Dosu, mention @dosu.