Merge branch 'main' into copilot-prov

Author: lukehinds

.github/workflows/import_packages.yml

@@ -30,6 +30,19 @@ jobs:
           git lfs install
           git lfs pull
 
+    - name: Download json data
+      id: download-json-data
+      uses: dawidd6/action-download-artifact@v7
+      with:
+        repo: stacklok/codegate-data
+        workflow: ".github/workflows/generate-artifact.yml"
+        workflow_conclusion: success
+        name: jsonl-files
+        path: /tmp/
+        name_is_regexp: true
+        skip_unpack: false
+        if_no_artifact_found: ignore          
+
     - name: Download artifact
       if: ${{ github.event.inputs.enable_artifact_download == 'true' }}    
       id: download-artifact
@@ -57,9 +70,9 @@ jobs:
         export BACKUP_FOLDER=backup
         # Conditionally export the variables only if artifact download is enabled
         if [ "${{ github.event.inputs.enable_artifact_download }}" == "true" ]; then
-          python scripts/import_packages.py
+          python scripts/import_packages.py --jsonl-dir /tmp/jsonl-files/
         else
-          python scripts/import_packages.py --restore_backup False
+          python scripts/import_packages.py --restore-backup False --jsonl-dir /tmp/jsonl-files/
         fi
 
     - name: 'Upload Backup Files'

Dockerfile

@@ -22,7 +22,7 @@ RUN poetry config virtualenvs.create false && \
 COPY . /app
 
 # Build the webapp
-FROM node:23.3-slim AS webbuilder
+FROM node:22-slim AS webbuilder
 
 # Install curl for downloading the webapp from GH and unzip to extract it
 RUN apt-get update && apt-get install -y --no-install-recommends \
@@ -98,9 +98,28 @@ EXPOSE 80
 # Set the PYTHONPATH environment variable
 ENV PYTHONPATH=/app/src
 
-# Define an argument for vlm_url with a default value
-ENV VLLM_URL=https://inference.codegate.ai
+# Expose additional env vars
+ENV CODEGATE_VLLM_URL=https://inference.codegate.ai
+ENV CODEGATE_OPENAI_URL=
+ENV CODEGATE_ANTHROPIC_URL=
+ENV CODEGATE_OLLAMA_URL=http://host.docker.internal:11434
+ENV CODEGATE_APP_LOG_LEVEL=WARNING
+ENV CODEGATE_LOG_FORMAT=TEXT
+
+# Copy the initial models in the image to default models
+RUN mkdir -p /app/default_models && cp /app/codegate_volume/models/* /app/default_models/
+
+# Define volume for persistent data
+VOLUME ["/app/codegate_volume/"]
+
+# This has to be performed after copying from the builder stages.
+# Otherwise, the permissions will be reset to root.
+USER root
+RUN mkdir -p /app/codegate_volume/db
+# Make codegate user the owner of codegate_volume directory to allow writing to it
+RUN chown -R codegate /app/codegate_volume
+USER codegate
 
 # Set the container's default entrypoint
 EXPOSE 8989
-ENTRYPOINT ["/app/scripts/entrypoint.sh", "/tmp/weaviate_backup", "backup"]
+ENTRYPOINT ["/app/scripts/entrypoint.sh"]

README.md

@@ -51,7 +51,6 @@ Unlike E.T., your code never phones home! 🛸 Codegate is designed with privacy
 Make sure you have these tools installed:
 
 - 🐳 [Docker](https://docs.docker.com/get-docker/)
-- 🔧 [Docker Compose](https://docs.docker.com/compose/install/)
 - 🛠️ [jq](https://stedolan.github.io/jq/download/)
 - 💻 [VSCode](https://code.visualstudio.com/download)
 
@@ -150,11 +149,29 @@ make image-build
 
 ### Run the Container
 ```bash
-# Basic usage
-docker run -p 8989:8989 codegate:latest
+# Basic usage with local image
+docker run -p 8989:8989 -p 8990:80 codegate:latest
 
-# With persistent data
-docker run -p 8989:8989 -v /path/to/volume:/app/weaviate_data codegate:latest
+# With pre-built pulled image
+docker pull ghcr.io/stacklok/codegate/codegate:latest
+docker run --name codegate -d -p 8989:8989 -p 8990:80 ghcr.io/stacklok/codegate/codegate:latest
+
+# It will mount a volume to /app/codegate_volume
+# The directory supports storing Llama CPP models under subidrectoy /models
+# A sqlite DB with the messages and alerts is stored under the subdirectory /db
+docker run --name codegate -d -v /path/to/volume:/app/codegate_volume -p 8989:8989 -p 8990:80 ghcr.io/stacklok/codegate/codegate:latest
+```
+
+### Exposed parameters
+- CODEGATE_VLLM_URL: URL for the inference engine (defaults to [https://inference.codegate.ai](https://inference.codegate.ai))
+- CODEGATE_OPENAI_URL: URL for OpenAI inference engine (defaults to [https://api.openai.com/v1](https://api.openai.com/v1))
+- CODEGATE_ANTHROPIC_URL: URL for Anthropic inference engine (defaults to [https://api.anthropic.com/v1](https://api.anthropic.com/v1))
+- CODEGATE_OLLAMA_URL: URL for OLlama inference engine (defaults to [http://localhost:11434/api](http://localhost:11434/api))
+- CODEGATE_APP_LOG_LEVEL: Level of debug desired when running the codegate server (defaults to WARNING, can be ERROR/WARNING/INFO/DEBUG)
+- CODEGATE_LOG_FORMAT: Type of log formatting desired when running the codegate server (default to TEXT, can be JSON/TEXT)
+
+```bash
+docker run -p 8989:8989 -p 8990:80 -e CODEGATE_OLLAMA_URL=http://1.2.3.4:11434/api ghcr.io/stacklok/codegate/codegate:latest
 ```
 
 ## 🤝 Contributing

models/all-minilm-L6-v2-q5_k_m.gguf renamed to codegate_volume/models/all-minilm-L6-v2-q5_k_m.gguf

@@ -19,7 +19,7 @@ log_level: "INFO"  # One of: ERROR, WARNING, INFO, DEBUG
 ##
 
 # Model to use for chatting
-model_base_path: "./models"
+model_base_path: "./codegate_volume/models"
 
 # Context length of the model
 chat_model_n_ctx: 32768

config.yaml

@@ -50,7 +50,7 @@ server_key: "server.key"   # Server key file name
 ##
 
 # Model to use for chatting
-chat_model_path: "./models/qwen2.5-coder-1.5b-instruct-q5_k_m.gguf"
+chat_model_path: "./codegate_volume/models/qwen2.5-coder-1.5b-instruct-q5_k_m.gguf"
 
 # Context length of the model
 chat_model_n_ctx: 32768