Skip to main content

Unstract interface for LLMs, Embeddings and VectorDBs

Project description

Unstract

No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents

Unstract Adapters

This is Unstract's python package which helps to configure to a number of different LLMs, Embeddings and VectorDBs.

LLMs

The following LLMs are supported:

LLM Version
OpenAI 1.3.9
Azure OpenAI 1.3.9
Anthropic 0.7.8
PaLM 0.3.1
Replicate 0.22.0
AnyScale 0.5.165
Mistral 0.0.8

Embeddings

The following Embeddings are supported:

Embedding Version
OpenAI 1.3.9
Azure OpenAI 1.3.9
Qdrant FastEmbed 0.1.3
HuggingFace 0.0.1
PaLM 0.3.1

VectorDBs

The following VectorDBs are supported:

Vector DB Version
Milvus 2.3.4
Pinecone 2.2.4
Postgres 0.2.4
Qdrant 1.7.0
Supabase 2.2.1
Weaviate 3.25.3

Installation

Local Development

To get started with local development,

  • Create and source a virtual environment if you haven't already following these steps.
  • If you're using Mac, install the below library needed for PyMSSQL
brew install pkg-config freetds
  • Install the required dependencies with
pdm install

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

unstract_adapters-0.8.1.tar.gz (74.2 kB view details)

Uploaded Source

Built Distribution

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

unstract_adapters-0.8.1-py3-none-any.whl (129.6 kB view details)

Uploaded Python 3

File details

Details for the file unstract_adapters-0.8.1.tar.gz.

File metadata

  • Download URL: unstract_adapters-0.8.1.tar.gz
  • Upload date:
  • Size: 74.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: pdm/2.12.3 CPython/3.8.10

File hashes

Hashes for unstract_adapters-0.8.1.tar.gz
Algorithm Hash digest
SHA256 6abb54a4bcd4df03badbfbb2c88cd1323fcef3b1a5115fc456aa22a7ec10d6d0
MD5 5d1a83e055c90fbd598dc037d439bc4c
BLAKE2b-256 341eb333e46a167fb6afb1b57a5c6e373447a3a907ebe7af4ec6aec6852e7250

See more details on using hashes here.

File details

Details for the file unstract_adapters-0.8.1-py3-none-any.whl.

File metadata

File hashes

Hashes for unstract_adapters-0.8.1-py3-none-any.whl
Algorithm Hash digest
SHA256 dddb7233d033648181c1b957d784ac5148c1d8623429bc7faf41fa0b5d993247
MD5 78c514d904adb00ce5c24715fe1527cf
BLAKE2b-256 9a297c5ca9cfc577edc18b3eb9f10b26105f7c38312f1522e5170ebabe2857ca

See more details on using hashes here.

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