Fix local dev setup

.env.example

@@ -65,6 +65,9 @@ JINA_CODE_API_KEY=""
 VECTOR_SIZES="384,512,768,1024,1536,3072"
 RUST_LOG="INFO"
 BM25_ACTIVE="true"
+PAGEFIND_CDN_BASE_URL="lZP8X4h0Q5Sj2ZmV,aAmu1W92T6DbFUkJ,DZ5pMvz8P1kKNH0r,QAqwvKh8rI5sPmuW,YMwgsBz7jLfN0oX8"
+SHOPIFY_SECRET_KEY="foobar"
+GROQ_API_KEY="loremipsum"
 
 ##### Firecrawl #####
 NUM_WORKERS_PER_QUEUE=8 

.gitignore

@@ -97,4 +97,6 @@ pdf2md/ch_migrations/chm.toml
 clients/trieve-shopify-extension/shopify.app.skept-trieve-extension-test.toml
 clients/trieve-shopify-extension/shopify.app.skept-laptop-trieve-extension.toml
 charts/charts/**/*.tgz
-clients/trieve-shopify-extension/.env.skept-trieve-extension-test
+clients/trieve-shopify-extension/.env.skept-trieve-extension-test
+.idea
+docker-compose-cpu-embeddings.override.yml

README.md

@@ -56,7 +56,7 @@
 
 **Are we missing a feature that your use case would need?** - call us at [628-222-4090](mailto:+16282224090), make a [Github issue](https://github.com/devflowinc/trieve/issues), or join the [Matrix community](https://matrix.to/#/#trieve-general:trieve.ai) and tell us! We are a small company who is still very hands-on and eager to build what you need; professional services are available.
 
-## Local development with Linux
+## Local Development
 
 ### Installing via Smithery
 
@@ -66,8 +66,9 @@ To install Trieve for Claude Desktop automatically via [Smithery](https://smithe
 npx -y @smithery/cli install trieve-mcp-server --client claude
 ```
 
-### Debian/Ubuntu Packages needed packages
+### System Dependencies
 
+#### Linux (Debian/Ubuntu)
 ```sh
 sudo apt install curl \
 gcc \
@@ -81,12 +82,23 @@ libssl-dev \
 openssl
 ```
 
-### Arch Packages needed
-
+#### Linux (Arch)
 ```sh
 sudo pacman -S base-devel postgresql-libs
 ```
 
+#### MacOS
+```sh
+# Install Xcode command line tools
+xcode-select --install
+
+# Install Homebrew if not already installed
+/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
+
+# Install required packages
+brew install pkg-config openssl
+```
+
 ### Install NodeJS and Yarn
 
 You can install [NVM](https://github.com/nvm-sh/nvm) using its install script.
@@ -142,9 +154,9 @@ cp .env.dashboard ./frontends/dashboard/.env
 2. Replace the value for `LLM_API_KEY` to be your own OpenAI API key.
 3. Replace the value for `OPENAI_API_KEY` to be your own OpenAI API key.
 
-### Export the following keys in your terminal for local dev
+### Override the following keys in your terminal for local dev
 
-The PAGEFIND_CDN_BASE_URL and S3_SECRET_KEY_CSVJSONL could be set to a random list of strings.
+The PAGEFIND_CDN_BASE_URL and S3_SECRET_KEY_CSVJSONL can be set to a random list of strings.
 
 ```
 export OPENAI_API_KEY="your_OpenAI_api_key" \
@@ -163,6 +175,35 @@ cat .env.chat .env.search .env.server .env.docker-compose > .env
 ./convenience.sh -l
 ```
 
+### Start embedding servers
+
+We offer 2 docker-compose files for embedding servers. One for GPU and one for CPU.
+
+```sh
+docker compose -f docker-compose-cpu-embeddings.yml up -d
+```
+
+or
+
+```sh
+docker compose -f docker-compose-gpu-embeddings.yml up -d
+```
+
+* Note on embedding servers. If you want to use a separate GPU enabled device for embedding servers you will need to update the following parameters
+
+```
+SPARSE_SERVER_QUERY_ORIGIN
+SPARSE_SERVER_DOC_ORIGIN
+EMBEDDING_SERVER_ORIGIN
+SPARSE_SERVER_QUERY_ORIGIN
+```
+
+#### Using CPU embeddings on MacOS
+```
+cp docker-compose-cpu-embeddings.override.mac docker-compose-cpu-embeddings.override.yml
+docker-compose -f docker-compose-cpu-embeddings.yml -f docker-compose-cpu-embeddings.override.yml docker up -d
+```
+
 ### Install front-end packages for local dev
 
 ```

docker-compose-cpu-embeddings.override.mac

@@ -0,0 +1,21 @@
+# Docker Compose overrides for macOS development with CPU embeddings
+# To use this file: docker-compose -f docker-compose-cpu-embeddings.yml -f docker-compose-cpu-embeddings.override.yml up
+# For Linux development, don't include this override file
+
+version: '3'
+
+services:
+  splade-doc:
+    platform: linux/amd64
+
+  splade-query:
+    platform: linux/amd64
+
+  jina:
+    platform: linux/amd64
+
+  bgem3:
+    platform: linux/amd64
+
+  reranker:
+    platform: linux/amd64

docker-compose-cpu-embeddings.yml

@@ -27,15 +27,15 @@ services:
       - ./data:/data
 
   bgem3:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
     command: --model-id BAAI/bge-m3 --revision main
     ports:
       - "7000:80"
     volumes:
       - ./data:/data
 
   reranker:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.8.2
     command: --model-id BAAI/bge-reranker-base --revision main
     ports:
       - "8000:80"

docker-compose.override.yml

@@ -0,0 +1,7 @@
+version: '3'
+
+services:
+  clickhouse-db:
+    environment:
+      # Loop back to the host machine to reach the embedding server
+      - EMBEDDING_SERVER_URL=http://host.docker.internal:6000

docker-compose.yml

@@ -245,8 +245,8 @@ services:
   dashboard:
     image: trieve/dashboard
     build:
-      context: ./frontends
-      dockerfile: ./dashboard/Dockerfile
+      context: .
+      dockerfile: ./frontends/dashboard/Dockerfile
     networks:
       - app-network
     ports:
@@ -261,8 +261,8 @@ services:
   chat:
     image: trieve/chat
     build:
-      context: ./frontends
-      dockerfile: ./chat/Dockerfile
+      context: .
+      dockerfile: ./frontends/chat/Dockerfile
     networks:
       - app-network
     ports:
@@ -275,8 +275,8 @@ services:
   search:
     image: trieve/search
     build:
-      context: ./frontends
-      dockerfile: /search/
+      context: .
+      dockerfile: ./frontends/search/Dockerfile
     networks:
       - app-network
     ports: