---
AI Chat Bot with Plugins (Home Assistant, Vehicle Lookup, DuckDuckGo Search)
[](https://drone.va.reichard.io/evan/minyma)
## Plugins
### Vehicle Lookup API
This utilizes Carvana's undocumented API to lookup details on a vehicle.
```
User: What vehicle is NY plate HELLO?
Assistant: The vehicle corresponding to NY plate HELLO is a 2016 MAZDA CX-5
Grand Touring Sport Utility 4D with VIN JM3KE4DY6G0672552.
```
### Home Assistant API
This utilizes Home Assistants [Conversational API](https://developers.home-assistant.io/docs/intent_conversation_api/).
```
User: Turn off the living room lights
Assistant: The living room lights have been turned off. Is there anything else I can assist you with?
User: Turn on the living room lights
Assistant: The living room lights have been turned on successfully.
```
### DuckDuckGo
This utilizes DuckDuckGo Search by scraping the top 5 results.
```
User: Tell me about Evan Reichard
Assistant: Evan Reichard is a Principal Detection and Response Engineer based
in the Washington DC-Baltimore Area. He has been in this role since
August 2022. Evan has created a browser extension that helps SOC
analysts and saves them over 300 hours per month. Additionally,
there are three professionals named Evan Reichard on LinkedIn and
there are also profiles of people named Evan Reichard on Facebook.
```
## Running Server
```bash
# Locally (See "Development" Section)
export OPENAI_API_KEY=`cat openai_key`
export HOME_ASSISTANT_API_KEY=`cat ha_key`
export HOME_ASSISTANT_URL=https://some-url.com
minyma server run
# Docker Quick Start
docker run \
-p 5000:5000 \
-e OPENAI_API_KEY=`cat openai_key` \
-e DATA_PATH=/data \
-v ./data:/data \
gitea.va.reichard.io/evan/minyma:latest
```
The server will now be accessible at `http://localhost:5000`
## Normalizing & Loading Data
Minyma is designed to be extensible. You can add normalizers and vector db's
using the appropriate interfaces defined in `./minyma/normalizer.py` and
`./minyma/vdb.py`. At the moment the only supported database is `chroma`
and the only supported normalizer is the `pubmed` normalizer.
To normalize data, you can use Minyma's `normalize` CLI command:
```bash
minyma normalize \
--filename ./pubmed_manuscripts.jsonl \
--normalizer pubmed \
--database chroma \
--datapath ./chroma
```
The above example does the following:
- Uses the `pubmed` normalizer
- Normalizes the `./pubmed_manuscripts.jsonl` raw dataset [0]
- Loads the output into a `chroma` database and persists the data to the `./chroma` directory
**NOTE:** The above dataset took about an hour to normalize on my MPB M2 Max
[0] https://huggingface.co/datasets/TaylorAI/pubmed_author_manuscripts/tree/main
## Configuration
| Environment Variable | Default Value | Description |
| -------------------- | ------------- | ---------------------------------------------------------------------------------- |
| OPENAI_API_KEY | NONE | Required OpenAI API Key for ChatGPT access. |
| DATA_PATH | ./data | The path to the data directory. Chroma will store its data in the `chroma` subdir. |
# Development
```bash
# Initiate
python3 -m venv venv
. ./venv/bin/activate
# Local Development
pip install -e .
# Creds
export OPENAI_API_KEY=`cat openai_key`
# Docker
make docker_build_local
```
# Notes
This is the first time I'm doing anything LLM related, so it was an adventure.
Initially I was entertaining OpenAI's Embedding API with plans to load embeddings
into Pinecone, however initial calculations with `tiktoken` showed that generating
embeddings would cost roughly $250 USD.
Fortunately I found [Chroma](https://www.trychroma.com/), which basically solved
both of those issues. It allowed me to load in the normalized data and automatically
generated embeddings for me.
In order to fit into OpenAI ChatGPT's token limit, I limited each document to roughly
1000 words. I wanted to make sure I could add the top two matches as context while
still having enough headroom for the actual question from the user.
A few notes:
- Context is not carried over from previous messages
- I "stole" the prompt that is used in LangChain (See `oai.py`). I tried some variations without much (subjective) improvement.
- A generalized normalizer format. This should make it fairly easy to use completely different data. Just add a new normalizer that implements the super class.
- Basic web front end with TailwindCSS