Connect ArangoDB to LlamaIndex for Data Ingestion
Load documents from an ArangoDB collection into LlamaIndex with query and field filtering.
Why it matters
Integrate your ArangoDB data into LlamaIndex for advanced AI applications. This asset enables seamless data loading from ArangoDB collections, preparing your data for retrieval-augmented generation and other AI tasks.
Outcomes
What it gets done
Load documents from specified ArangoDB collections.
Configure data fetching with custom query parameters.
Select specific fields for data extraction.
Prepare ArangoDB data for LlamaIndex ingestion.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/li-reader-readers-arango-db | bash Overview
LlamaIndex Readers Integration: ArangoDB
A LlamaIndex reader that loads documents from an ArangoDB collection via a find()-style query with configurable field content. Use when you already store data in ArangoDB and want a query-filtered subset loaded for retrieval.
What it does
The ArangoDB Reader loads documents from ArangoDB into LlamaIndex. The user specifies an ArangoDB instance to initialize the reader, then specifies a collection name and query parameters to fetch the relevant documents.
SimpleArangoDBReader is initialized with a host (or an ArangoClient instance can be passed instead). load_data then takes a username, password, db_name, and collection_name, along with a query_dict that gets passed directly into the collection's find() call to filter which documents are fetched, and a field_names list (defaulting to ["text"]) naming which document attributes should be loaded as content.
When to use - and when NOT to
Use it when you need a specific, query-filtered subset of documents from an ArangoDB collection loaded into LlamaIndex, with control over which fields become the document content via field_names. Do not use it as a general ArangoDB administration tool; it is a read-only loader built around a find()-style query, not a way to write or manage the database.
Capabilities
load_data connects to an ArangoDB instance, runs a find()-style query against a named collection, and returns matching documents built from specified field_names.
How to install
pip install llama-index-readers-arango-db
Requires ArangoDB connection details (host, username, password) and a target collection name.
Who it's for
Developers who already store data in ArangoDB and want a specific, query-filtered subset of a collection loaded into LlamaIndex for retrieval or question-answering.
Source README
LlamaIndex Readers Integration: ArangoDB
pip install llama-index-readers-arango-db
This loader loads documents from ArangoDB. The user specifies an ArangoDB instance to
initialize the reader. They then specify the collection name and query parameters to
fetch the relevant docs.
Usage
Here's an example usage of the SimpleArangoDBReader.
import os
from llama_index.readers.arango_db import SimpleArangoDBReader
host = "<host>"
db_name = "<db_name>"
collection_name = "<collection_name>"
### query_dict is passed into db.collection.find()
query_dict = {}
### Attribute of interests to load, by default ["text"]
field_names = ["title", "description"]
reader = SimpleArangoDBReader(host) # or pass ArangoClient
documents = reader.load_data(
username,
password,
db_name,
collection_name,
query_dict=query_dict,
field_names=field_names,
)
A demo notebook is available here.
This loader is designed to be used as a way to load data into LlamaIndex.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.