v0.0.3

README.md

@@ -1,5 +1,5 @@
 # Honcho
-![Static Badge](https://img.shields.io/badge/Version-0.0.2-blue)
+![Static Badge](https://img.shields.io/badge/Version-0.0.3-blue)
 [![Discord](https://img.shields.io/discord/1016845111637839922?style=flat&logo=discord&logoColor=23ffffff&label=Plastic%20Labs&labelColor=235865F2)](https://discord.gg/plasticlabs)
 ![GitHub License](https://img.shields.io/github/license/plastic-labs/honcho)
 ![GitHub Repo stars](https://img.shields.io/github/stars/plastic-labs/honcho)
@@ -50,14 +50,21 @@ poetry install # install dependencies
    connection_uri. For testing sqlite is fine. The below example uses an
    in-memory sqlite database. 
 
-> Honcho has been tested with Postgresql and SQLite
+> Honcho has been tested with Postgresql and PGVector
 
 ```env
-DATABASE_TYPE=sqlite
-CONNECTION_URI=sqlite://
+DATABASE_TYPE=postgres
+CONNECTION_URI=postgresql://testuser:testpwd@localhost:5432/honcho
 ```
 
-3. Run the API via uvicorn
+3. launch a postgresd with pgvector enabled with docker-compose
+
+```bash
+cd honcho/api/local
+docker-compose up -d
+```
+
+4. Run the API via uvicorn
 
 ```bash
 cd honcho/api # change to the api directory
@@ -86,7 +93,7 @@ Docs](https://fly.io/docs/getting-started/) to setup your environment and the
 `flyctl`. 
 
 
-Once `flyctl` is set up use the the following commands to launch the application:
+Once `flyctl` is set up use the following commands to launch the application:
 
 ```bash
 cd honcho/api

api/.env.template

@@ -1,2 +1,7 @@
 DATABASE_TYPE=sqlite
 CONNECTION_URI=sqlite://
+
+DATABASE_TYPE=postgres
+CONNECTION_URI=postgresql://testuser:testpwd@localhost:5432/honcho
+
+OPENAI_API_KEY=

api/CHANGELOG.md

@@ -4,6 +4,22 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/)
 and this project adheres to [Semantic Versioning](http://semver.org/).
 
+## [0.0.3] — 2024-02-15
+
+### Added
+
+* Collections table to reference a collection of embedding documents
+* Documents table to hold vector embeddings for RAG workflows
+* Local scripts for running a postgres database with pgvector installed
+* OpenAI Dependency for embedding models
+* PGvector dependency for vector db support
+
+### Changed
+
+* session_data is now metadata
+* session_data is a JSON field used python `dict` for compatability
+
+
 ## [0.0.2] — 2024-02-01
 
 ### Added

api/local/docker-compose.yml

@@ -0,0 +1,14 @@
+services:
+  db:
+    hostname: db
+    image: ankane/pgvector
+    ports:
+     - 5432:5432
+    restart: always
+    environment:
+      - POSTGRES_DB=honcho
+      - POSTGRES_USER=testuser
+      - POSTGRES_PASSWORD=testpwd
+      - POSTGRES_HOST_AUTH_METHOD=trust
+    volumes:
+     - ./init.sql:/docker-entrypoint-initdb.d/init.sql

api/local/init.sql

@@ -0,0 +1 @@
+CREATE EXTENSION IF NOT EXISTS vector;

api/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "honcho"
-version = "0.0.2"
+version = "0.0.3"
 description = "Honcho Server"
 authors = ["Plastic Labs <[email protected]>"]
 readme = "README.md"
@@ -14,6 +14,8 @@ sqlalchemy = "^2.0.25"
 psycopg2-binary = "^2.9.9"
 slowapi = "^0.1.8"
 fastapi-pagination = "^0.12.14"
+pgvector = "^0.2.5"
+openai = "^1.12.0"
 
 
 [build-system]