Skip to main content

Embeddings interface for Ollama

Project description

Ellama

Embeddings library (i.e. vector database) built over Ollama.

from ellama import EllamaDB, Document

db = EllamaDB("test")
db.add_documents([
    Document(page_content="hello world", id="salutation"),
    Document(page_content="goodbye and goodnight", id="farewell")])
docs = db.similarity_search("Greetings, Earth!", k=1)
assert len(docs) == 1
assert docs[0].id == "salutation"

install

pip (CPU)

pip install "ellama[cpu]"

conda (GPU)

name: catch
channels: [pytorch, nvidia, conda-forge]
dependencies:
- langchain 1.*
- langchain-community
- faiss-gpu
- requests
- tqdm
- pip
- pip:
  - ellama 0.2.*

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ellama-0.3.0.tar.gz (5.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ellama-0.3.0-py3-none-any.whl (3.7 kB view details)

Uploaded Python 3

File details

Details for the file ellama-0.3.0.tar.gz.

File metadata

  • Download URL: ellama-0.3.0.tar.gz
  • Upload date:
  • Size: 5.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for ellama-0.3.0.tar.gz
Algorithm Hash digest
SHA256 4c73101cc139a4362914169fd5b61acec13dd89a5b55177c9b9f20b051d5dd26
MD5 0d3d0e0ca2fa225904689624b75a9811
BLAKE2b-256 4fecac8da499ebaaafa3f50bfd4cf11817ee3ff117ac63b520debb00637f51a8

See more details on using hashes here.

Provenance

The following attestation bundles were made for ellama-0.3.0.tar.gz:

Publisher: test.yml on casperdcl/ellama

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file ellama-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: ellama-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 3.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for ellama-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 bb5a4ed3e65fd83ba3ee4421acf4ca6dab82722f4658c4aa74d3744a6e800e58
MD5 152509fe176ece31e6927e7b29301b0b
BLAKE2b-256 a55dc6a7ec50ffbb941f79bcaefc378acd113041ed71cfded29794ed0a98278d

See more details on using hashes here.

Provenance

The following attestation bundles were made for ellama-0.3.0-py3-none-any.whl:

Publisher: test.yml on casperdcl/ellama

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page