ingest-anything 1.0.0

ingest-anything: from data to vector database effortlessly

ingest-anything

From data to vector database effortlessly

ingest-anything is a python package aimed at providing a smooth solution to ingest non-PDF files into vector databases, given that most ingestion pipelines are focused on PDF/markdown files. Leveraging chonkie, PdfItDown, Llamaindex, Sentence Transformers embeddings and Qdrant, ingest-anything gives you a fully-automated pipeline for document ingestion within few lines of code!

Find out more about ingest-anything on the Documentation website!

Workflow

For text files

• The input files are converted into PDF by PdfItDown
• The PDF text is extracted using LlamaIndex Docling reader
• The text is chunked exploiting Chonkie's functionalities
• The chunks are embedded thanks to Sentence Transformers models
• The embeddings are loaded into a Qdrant vector database

For code files

• The text is extracted from code files using LlamaIndex SimpleDirectoryReader
• The text is chunked exploiting Chonkie's CodeChunker
• The chunks are embedded thanks to Sentence Transformers models
• The embeddings are loaded into a Qdrant vector database

Installation and usage

ingest-anything can be installed using pip in the following way:

pip install ingest-anything
# or, for a faster installation
uv pip install ingest-anything

And is available in your python scripts:

• You can initialize the interface for text-based files like this:

from ingest_anything.ingestion import IngestAnything, QdrantClient, AsyncQdrantClient

coll_name = "Flowers"
client = QdrantClient("http://localhost:6333")
aclient = AsyncQdrantClient("http://localhost:6333")
ingestor = IngestAnything(qdrant_client=client, async_qdrant_client=aclient, collection_name=coll_name, hybrid_search=True)

• And ingest your files:

# with a list of files
ingestor.ingest(chunker="late", files_or_dir=['tests/data/test.docx', 'tests/data/test0.png', 'tests/data/test1.csv', 'tests/data/test2.json', 'tests/data/test3.md', 'tests/data/test4.xml', 'tests/data/test5.zip'], embedding_model="sentence-transformers/all-MiniLM-L6-v2")
# with a directory
ingestor.ingest(chunker="token", files_or_dir="tests/data", tokenizer="gpt2", embedding_model="sentence-transformers/all-MiniLM-L6-v2")

• You can also initialize the interface for code files

from ingest_anything.ingestion import IngestCode, QdrantClient, AsyncQdrantClient

coll_name = "go-code"
client = QdrantClient("http://localhost:6333")
aclient = AsyncQdrantClient("http://localhost:6333")
ingestor = IngestCode(qdrant_client=client, async_qdrant_client=aclient, collection_name=coll_name, hybrid_search=True)

• And then ingest your code files:

# with a list of files
ingestor.ingest(files=["tests/code/acronym.go", "tests/code/animal_magic.go", "tests/code/atbash_cipher_test.go"], embedding_model="sentence-transformers/all-MiniLM-L6-v2", language="go")

You can find a complete reference for the package in REFERENCE.md

Contributing

Contributions are always welcome!

Find contribution guidelines at CONTRIBUTING.md

License and Funding

This project is open-source and is provided under an MIT License.

If you found it useful, please consider funding it.