No project description provided
Project description
Relevance AI
A simple chain
1. Install and login
Install:
pip install relevanceai
Log in and create a project and api key:
import relevanceai as rai
rai.login()
or if you are in an automated environment, set these environment variables:
RELEVANCE_API_KEY=XXXX
2. Getting started
chain = rai.create(
name = "My chain",
description = "The greatest chain"
)
3. Add steps to the chain
Create a step for the chain
step = PromptCompletion(
prompt="Hello world",
)
You can run and test the individual step.
step.run()
Once you are comfortable with the step you can add it by
chain.add(step)
4. Run and test the chain
Run the chain
chain.run()
5. Configuring output
By default it'll return the full state and all outputs from each step. You can control it by:
chain.set_output(["answer"])
A chain with flexible inputs
1. Give your chain flexible inputs
Add input parameters
chain = rai.create(
name = "My chain",
description = "The greatest chain"
parameters = {
"name" : {"type" : "string"}
}
)
2. Define the parameters inside a step
step = PromptCompletion(
prompt="Hello world my name is ${name}",
)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file relevanceai-chains-1.0.1.tar.gz
.
File metadata
- Download URL: relevanceai-chains-1.0.1.tar.gz
- Upload date:
- Size: 9.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5fffc6e1f28c74f7bb85b98237373877a772ac873ef34327e9d205b7891568fd |
|
MD5 | b0abe4f0651821553fa8b18ea3ec8653 |
|
BLAKE2b-256 | 38dcb8c9acdec5a7b5745cff42e4cd1955ddd3fa741a86819c7bf675de6f8a83 |
File details
Details for the file relevanceai_chains-1.0.1-py3-none-any.whl
.
File metadata
- Download URL: relevanceai_chains-1.0.1-py3-none-any.whl
- Upload date:
- Size: 14.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3373cc3d7290853fa033a9938c853eb30b9a1c61d5dc0f5135191a6324f1de5a |
|
MD5 | 6af60934ad9f8813518436503294db60 |
|
BLAKE2b-256 | 0cd660ffd3dd2ddfdd49a1a529e898bee1bc37cb4997a107dadba7f2f910bda7 |