Release (#1)

Initial release

---------

Co-authored-by: Jia Huei Tan <tanjiahuei@gmail.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>

Author: 3 people

.dockerignore

@@ -0,0 +1,36 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.egg-info
+.pytest_cache
+.ipynb_checkpoints
+venv/
+*.png
+*.jpg
+*.npy
+*.geojson
+*.laz
+
+# Internal references, dependencies, temporary folders & files
+# .env
+**/__ref__/
+/dependencies/
+logs/
+*.log
+/datasets/
+/milvus_data/
+/vespa*/
+
+# pytest-cov
+**/.coverage*
+/junit
+/htmlcov
+/coverage.xml
+
+# pip
+**/build/
+
+# OS
+thumbs.db
+.DS_Store

.env

@@ -0,0 +1,27 @@
+# External API keys
+OPENAI_API_KEY=
+ANTHROPIC_API_KEY=
+COHERE_API_KEY=
+TOGETHER_API_KEY=
+
+# Service URLs
+DOCIO_URL=http://docio:6979/api/docio
+UNSTRUCTUREDIO_URL=http://unstructuredio:6989
+
+# Configuration
+SERVICE_KEY=
+OWL_PORT=6969
+OWL_WORKERS=1
+OWL_DB_DIR=db
+OWL_LOG_DIR=logs
+DOCIO_WORKERS=1
+DOCIO_DEVICE=cpu
+EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
+RERANKER_MODEL=cross-encoder/ms-marco-TinyBERT-L-2
+OWL_CONCURRENT_ROWS_BATCH_SIZE=3
+OWL_CONCURRENT_COLS_BATCH_SIZE=5
+
+# Frontend config
+FRONTEND_PORT=4000
+JAMAI_URL=http://owl:${OWL_PORT}
+PUBLIC_JAMAI_URL=

.flake8

@@ -0,0 +1,11 @@
+[flake8]
+max-line-length = 99
+select = C,E,F,W,B,B950
+extend-ignore = E203,E402,E501,F541,W503,F401
+extend-exclude =
+    .vscode/,
+    archive/,
+    build/,
+    configs/,
+    dependencies/,
+    venv/

.gitattributes

@@ -0,0 +1,49 @@
+### https://git-scm.com/docs/gitattributes
+
+# When `text` is set to "auto", the path is marked for automatic end-of-line conversion.
+# If Git decides that the content is text, its line endings are converted to LF on checkin.
+# When the file has been committed with CRLF, no conversion is done.
+# https://git-scm.com/docs/gitattributes#Documentation/gitattributes.txt-Settostringvalueauto
+* text=auto eol=lf
+
+# These files are text and should be normalized (Convert crlf => lf)
+# Setting the `text` attribute on a path enables end-of-line normalization and marks the path as a text file.
+# End-of-line conversion takes place without guessing the content type.
+# https://git-scm.com/docs/gitattributes#_text
+*.css text
+*.html text
+*.js text
+*.md text
+*.py text
+*.sh text
+
+# These files are binary and should be left untouched
+# `binary` is a built-in macro for `-text` `-diff` (ie unset `text` and `diff`)
+# https://git-scm.com/docs/gitattributes#_using_macro_attributes
+*.7z binary
+*.bin binary
+*.cu.o binary
+*.db binary
+*.doc binary
+*.docx binary
+*.gz binary
+*.jar binary
+*.jpeg binary
+*.jpg binary
+*.npy binary
+*.npz binary
+*.pcd binary
+*.pdf binary
+*.pkl binary
+*.png binary
+*.ppt binary
+*.pptx binary
+*.pth binary
+*.so binary
+*.xls binary
+*.xlsx binary
+*.zip binary
+
+# These files should not be processed by Linguist for language detection on GitHub.com
+*.p linguist-detectable=false
+*.gz linguist-detectable=false

.github/workflows/ci.yml

@@ -0,0 +1,172 @@
+name: CI
+
+on:
+  pull_request:
+    branches:
+      - main
+
+  push:
+    branches:
+      - main
+    tags:
+      - "v*"
+
+jobs:
+  python_tests:
+    name: Python unit tests
+    runs-on: ubuntu-latest-l
+    strategy:
+      matrix:
+        python-version: ["3.10"]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      #- name: Test API Key
+      #  run: |
+      #    response=$(curl --fail -s -H "Authorization: Bearer ${OPENAI_API_KEY}" https://api.openai.com/v1/engines)
+      #    echo "$response"
+      #    if [ $? -ne 0 ]; then
+      #      echo "API key test failed!"
+      #      exit 1
+      #    fi
+      #  env:
+      #    OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+
+      - name: Setup
+        run: |
+          set -e
+          cd clients/python
+          python -m pip install .[all]
+
+      - name: Check Docker Version
+        run: docker version
+
+      - name: Check Docker Compose Version
+        run: docker compose version
+
+      - name: Launch services
+        timeout-minutes: 15
+        run: |
+          set -e
+          export API_DEVICE=cpu
+          export EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
+          export RERANKER_MODEL=cross-encoder/ms-marco-TinyBERT-L-2
+
+          # Edit .env file
+          ORGS=$(printenv | grep API_KEY | xargs -I {} echo {} | cut -d '=' -f 1)
+          KEYS=$(printenv | grep API_KEY | xargs -I {} echo {} | cut -d '=' -f 2-)
+          # Convert them into arrays
+          ORG_ARRAY=($ORGS)
+          KEY_ARRAY=($KEYS)
+          # Loop through the ORG_ARRAY
+          for i in "${!ORG_ARRAY[@]}"; do
+            # Get the org and key
+            org="${ORG_ARRAY[$i]}"
+            key="${KEY_ARRAY[$i]}"
+            # Replace the org with the key in the .env file
+            sed -i "s/$org=.*/$org=$key/g" .env
+          done
+
+          docker compose -f docker/compose.cpu.yml up --quiet-pull -d
+
+          # Wait for the service to finish starting up
+          set +e
+          while true; do
+              docker ps
+              response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:${OWL_PORT:-6969}/health)
+              echo $response
+              if [ $response -eq 200 ]; then
+                  break
+              fi
+              printf "> Waiting for API service ...\n"
+              sleep 10
+          done
+          printf "> DONE\n"
+        env:
+          JAMAI_API_KEY: ${{ secrets.JAMAI_API_KEY }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
+          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
+          COMPOSE_DOCKER_CLI_BUILD: 1
+          DOCKER_BUILDKIT: 1
+
+      #- name: Test list models
+      #  run: |
+      #    response=$(curl --fail -s http://localhost:6969/api/v1/models)
+      #    echo "$response"
+      #    if [ $? -ne 0 ]; then
+      #      echo "list models test failed!"
+      #      exit 1
+      #    fi
+
+      #- name: Get docker compose logs
+      #  if: always()
+      #  run: |
+      #    docker compose -f docker/compose.cpu.yml logs
+
+      - name: Pytest
+        run: |
+          set -e
+          export JAMAI_API_BASE=http://localhost:6969/api
+          python -m pytest -vv --doctest-modules --junitxml=junit/test-results-${{ matrix.python-version }}.xml --cov-report=xml clients/python/tests
+
+      - name: Upload Pytest Test Results
+        uses: actions/upload-artifact@v4
+        with:
+          name: pytest-results-${{ matrix.python-version }}
+          path: junit/test-results-${{ matrix.python-version }}.xml
+        # Use always() to always run this step to publish test results when there are test failures
+        if: ${{ always() }}
+
+      #- name: Generate OpenAPI Json Schema
+      #  run: mkdir -p artifacts && curl http://127.0.0.1:7770/api/openapi.json >> ./artifacts/openapi.json
+
+      #- name: Upload OpenAPI Json Schema
+      #  uses: actions/upload-artifact@v4
+      #  with:
+      #    name: openapi-json
+      #    path: artifacts/openapi.json
+
+  # readmeio_update:
+  #   needs: python_tests
+  #   name: Push OpenAPI to ReadMe.io
+  #   runs-on: ubuntu-latest-l
+  #   strategy:
+  #     matrix:
+  #       python-version: ["3.10"]
+  #   steps:
+  #     - name: Checkout code
+  #       uses: actions/checkout@v4
+
+  #     - name: Download OpenAPI Json Schema
+  #       uses: actions/download-artifact@v4
+  #       with:
+  #         name: openapi-json
+  #         path: artifacts
+
+  #     # - name: Display structure of downloaded files
+  #     #   run: ls -R artifacts
+
+  #     # Run GitHub Action to sync OpenAPI file at ./path-to-file.json
+  #     - name: Update ReadMe API Reference Documentation
+  #       # We recommend specifying a fixed version, i.e. @v8
+  #       # Docs: https://docs.github.com/actions/using-workflows/workflow-syntax-for-github-actions#example-using-versioned-actions
+  #       uses: readmeio/rdme@v8
+  #       with:
+  #         rdme: openapi artifacts/openapi.json --key=${{ secrets.README_API_KEY }} --id=${{ secrets.API_DEFINITION_ID }}
+
+  #     # - name: Generate Stainless SDK
+  #     #   uses: stainless-api/upload-openapi-spec-action@main
+  #     #   with:
+  #     #     stainless_api_key: ${{ secrets.STAINLESS_API_KEY }}
+  #     #     input_path: "artifacts/openapi.json"
+  #     #     config_path: "ellm.stainless.yaml"
+  #     #     project_name: "jamai"

.github/workflows/lint.yml

@@ -0,0 +1,62 @@
+name: Linting Workflow
+
+on:
+  push:
+    branches:
+      - "*"
+
+jobs:
+  python_lint:
+    name: Python linting and formatting checks
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10"]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install linting libraries
+        run: |
+          set -e
+          cd clients/python
+          python3 -m pip install .[lint]
+
+      - name: Check Python files using Black
+        run: |
+          set -e
+          black --check --verbose --diff --config clients/python/pyproject.toml .
+
+      - name: Run flake8 lint tests (errors)
+        run: |
+          set -e
+          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+
+      - name: Run flake8 lint tests (warnings)
+        run: |
+          set -e
+          flake8 . --count --exit-zero --max-complexity=10 --max-line-length=99 --statistics
+
+  prettier_lint:
+    name: Prettier Checks
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: "16" # Specify the Node.js version you want to use
+
+      - name: Check files using Prettier
+        run: |
+          npm install -g prettier@3.1
+          prettier --check .