Embedbase
Seamless data integration for LLMs
Open-source API & SDK to integrate your data and easily hook them up to LLMs
Used by AVA and serving 100k request a day
Check out the docs for more info.
What is it
Embedbase is a dead-simple API to help you use VectorDBs and Embeddings Models without needing to host them! You can use embedbase to customize LLM (like ChatGPT!) and automatically feed them the right information.
Installation
npm i embedbase-js
// this examples shows how you can use embedbase to automatically add context in a ChatGPT prompt
import { createClient } from 'embedbase-js'
const question = 'What can I do with Embedbase API?'
const embedbase = createClient(
'https://api.embedbase.xyz',
'api-key')
const context = await embedbase
.dataset('my-documentation')
.createContext(question);
console.log(context)
/* [
"Embedbase API allows to store unstructured data...",
"Embedbase API has 3 main functions a) provides a plug and play solution to store embeddings b) makes it easy to connect to get the right data into llms c)..",
"Embedabase API is self-hostable...",
] */
const prompt =
`Based on the following context:\n${context.join()}\nAnswer the user's question: ${question}`
// for await allows you to stream answers
for await (const res of embedbase.generate(prompt)) {
console.log(res)
// You, can, use, ...
}
// answer:
// You can use the Embedbase API to store unstructured data and then use the data to connect it to LLMs
Table of Contents
What are people building
- Recommendation Engines: AVA uses Embedbase to help their users find related notes
- Chat with your data: Solpilot uses Embedbase to put smart contract integration on autopilot
- Talk to your docs: ChatGPT-powered search for markdown documentation
The fastest way to get started with Embedbase is signing up for free to Embedbase Cloud.
Supported Integrations
Connections
- Any data with the sdk or api
- Github
Vector DBs
- Supabase
- Postgres
- Qdrant
- Weaviate
- Redis
Embedding Models
- OpenAI Embeddings
- sentence-transformers
- T5
Docs and support
Check out our tutorials for step-by-step guides, how-to's, and best practices, our documentation is powered by GPT-4, so you can ask question directly.
Ask a question in our Discord community to get support.
Contributing
Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.
Self-hosting
Note: this render configuration works well for experimentation.
1 maintainer
Release files for embedbase 1.2.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| embedbase-1.2.8.tar.gz | 23.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| embedbase-1.2.8-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 51.0 kB
Release files / embedbase-1.2.8.tar.gz
| Download URL | embedbase-1.2.8.tar.gz |
|---|---|
| Size | 23.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4bbccbd298d09e0d16c2ec2b1309be690b79053f085d28460e807c6e96f14f03
|
|
BLAKE2b-256 checksum How to use checksums |
1caf4969e51b304385798f1efc846ec4cc6f23bcda403561c2da60583d68133c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.4.2 CPython/3.11.3 Darwin/22.4.0
|
Release files / embedbase-1.2.8-py3-none-any.whl
| Download URL | embedbase-1.2.8-py3-none-any.whl |
|---|---|
| Size | 27.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4bc1310795ab06fb575e48eec2092edc78313746a0f138768010511cd97f301f
|
|
BLAKE2b-256 checksum How to use checksums |
b862f7336abcaf52aa6df1144b5334e00057304905a4ec0f12ed29da90ea9470
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.4.2 CPython/3.11.3 Darwin/22.4.0
|
