examples: use gallery in chatbot-ui, add flowise (#438)

Signed-off-by: mudler <mudler@mocaccino.org>
renovate/github.com-imdario-mergo-1.x
Ettore Di Giacinto 1 year ago committed by GitHub
parent 577d36b596
commit 11af09faf3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
  1. 1
      README.md
  2. 8
      examples/README.md
  3. 12
      examples/chatbot-ui/README.md
  4. 15
      examples/chatbot-ui/docker-compose.yaml
  5. 1
      examples/chatbot-ui/models/completion.tmpl
  6. 16
      examples/chatbot-ui/models/gpt-3.5-turbo.yaml
  7. 4
      examples/chatbot-ui/models/gpt4all.tmpl
  8. 26
      examples/flowise/README.md
  9. 37
      examples/flowise/docker-compose.yaml

@ -169,6 +169,7 @@ Feel free to open up a PR to get your project listed!
- [Spark](https://github.com/cedriking/spark)
- [autogpt4all](https://github.com/aorumbayev/autogpt4all)
- [Mods](https://github.com/charmbracelet/mods)
- [Flowise](https://github.com/FlowiseAI/Flowise)
## Short-term roadmap

@ -22,6 +22,14 @@ This integration shows how to use LocalAI with [mckaywrigley/chatbot-ui](https:/
[Check it out here](https://github.com/go-skynet/LocalAI/tree/master/examples/chatbot-ui/)
### Flowise
_by [@mudler](https://github.com/mudler)_
This example shows how to use [FlowiseAI/Flowise](https://github.com/FlowiseAI/Flowise) with LocalAI.
[Check it out here](https://github.com/go-skynet/LocalAI/tree/master/examples/flowise/)
### Discord bot
_by [@mudler](https://github.com/mudler)_

@ -4,22 +4,18 @@ Example of integration with [mckaywrigley/chatbot-ui](https://github.com/mckaywr
![Screenshot from 2023-04-26 23-59-55](https://user-images.githubusercontent.com/2420543/234715439-98d12e03-d3ce-4f94-ab54-2b256808e05e.png)
## Setup
## Run
In this example LocalAI will download the gpt4all model and set it up as "gpt-3.5-turbo". See the `docker-compose.yaml`
```bash
# Clone LocalAI
git clone https://github.com/go-skynet/LocalAI
cd LocalAI/examples/chatbot-ui
# (optional) Checkout a specific LocalAI tag
# git checkout -b build <TAG>
# Download gpt4all-j to models/
wget https://gpt4all.io/models/ggml-gpt4all-j.bin -O models/ggml-gpt4all-j
# start with docker-compose
docker-compose up -d --pull always
docker-compose up --pull always
# or you can build the images with:
# docker-compose up -d --build
```

@ -3,6 +3,14 @@ version: '3.6'
services:
api:
image: quay.io/go-skynet/local-ai:latest
# As initially LocalAI will download the models defined in PRELOAD_MODELS
# you might need to tweak the healthcheck values here according to your network connection.
# Here we give a timespan of 20m to download all the required files.
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
interval: 1m
timeout: 20m
retries: 20
build:
context: ../../
dockerfile: Dockerfile
@ -11,11 +19,16 @@ services:
environment:
- DEBUG=true
- MODELS_PATH=/models
# You can preload different models here as well.
# See: https://github.com/go-skynet/model-gallery
- 'PRELOAD_MODELS=[{"url": "github:go-skynet/model-gallery/gpt4all-j.yaml", "name": "gpt-3.5-turbo"}]'
volumes:
- ./models:/models:cached
command: ["/usr/bin/local-ai" ]
chatgpt:
depends_on:
api:
condition: service_healthy
image: ghcr.io/mckaywrigley/chatbot-ui:main
ports:
- 3000:3000

@ -1,16 +0,0 @@
name: gpt-3.5-turbo
parameters:
model: ggml-gpt4all-j
top_k: 80
temperature: 0.2
top_p: 0.7
context_size: 1024
stopwords:
- "HUMAN:"
- "GPT:"
roles:
user: " "
system: " "
template:
completion: completion
chat: gpt4all

@ -1,4 +0,0 @@
The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
### Prompt:
{{.Input}}
### Response:

@ -0,0 +1,26 @@
# flowise
Example of integration with [FlowiseAI/Flowise](https://github.com/FlowiseAI/Flowise).
![Screenshot from 2023-05-30 18-01-03](https://github.com/go-skynet/LocalAI/assets/2420543/02458782-0549-4131-971c-95ee56ec1af8)
You can check a demo video in the Flowise PR: https://github.com/FlowiseAI/Flowise/pull/123
## Run
In this example LocalAI will download the gpt4all model and set it up as "gpt-3.5-turbo". See the `docker-compose.yaml`
```bash
# Clone LocalAI
git clone https://github.com/go-skynet/LocalAI
cd LocalAI/examples/flowise
# start with docker-compose
docker-compose up --pull always
```
## Accessing flowise
Open http://localhost:3000.

@ -0,0 +1,37 @@
version: '3.6'
services:
api:
image: quay.io/go-skynet/local-ai:latest
# As initially LocalAI will download the models defined in PRELOAD_MODELS
# you might need to tweak the healthcheck values here according to your network connection.
# Here we give a timespan of 20m to download all the required files.
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
interval: 1m
timeout: 20m
retries: 20
build:
context: ../../
dockerfile: Dockerfile
ports:
- 8080:8080
environment:
- DEBUG=true
- MODELS_PATH=/models
# You can preload different models here as well.
# See: https://github.com/go-skynet/model-gallery
- 'PRELOAD_MODELS=[{"url": "github:go-skynet/model-gallery/gpt4all-j.yaml", "name": "gpt-3.5-turbo"}]'
volumes:
- ./models:/models:cached
command: ["/usr/bin/local-ai" ]
flowise:
depends_on:
api:
condition: service_healthy
image: flowiseai/flowise
ports:
- 3000:3000
volumes:
- ~/.flowise:/root/.flowise
command: /bin/sh -c "sleep 3; flowise start"
Loading…
Cancel
Save