Merge pull request #4 from arcee-ai/setup-repo

setup repo

.github/CODEOWNERS

@@ -0,0 +1 @@
+@Jacobsolawetz @ben-epstein

.github/workflows/publish.yml

@@ -0,0 +1,40 @@
+name: publish
+
+on:
+  release:
+    types: [created]
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.11"]
+      fail-fast: false
+    steps:
+      - name: checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: apt-get update
+        run: sudo apt-get update -y
+
+      - name: set up python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "pip"
+          cache-dependency-path: "pyproject.toml"
+
+      - name: install invoke
+        run: pip install invoke
+
+      - name: build
+        run: inv build
+
+      - name: publish
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.TWINE_TOKEN }}
+        run: inv publish

.github/workflows/test.yml

@@ -0,0 +1,35 @@
+name: PR Test
+
+on:
+  pull_request:
+    branches:
+      - main
+    paths:
+      - "arcee/**"
+
+jobs:
+  test_lint:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version-file: ".python-version"
+          cache: pip
+          cache-dependency-path: "**/pyproject.toml"
+
+      - name: install invoke
+        run: pip install invoke
+
+      - name: install dependencies
+        run: inv install --no-editable
+
+      - name: Run inv lint
+        run: inv lint
+
+#      - name: Run tests
+#        run: inv test

.gitignore

@@ -2,6 +2,7 @@
 __pycache__/
 *.py[cod]
 *$py.class
+.idea
 
 # C extensions
 *.so
@@ -81,9 +82,6 @@ target/
 profile_default/
 ipython_config.py
 
-# pyenv
-.python-version
-
 # pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
 #   However, in case of collaboration, if having platform-specific dependencies or dependencies

.python-version

@@ -0,0 +1 @@
+3.11

README.md

@@ -65,3 +65,38 @@ import arcee
 med_dalm = arcee.get_dalm("medical_dalm")
 med_dalm.retrieve("my query")
 ```
+
+# Contributing
+
+We use `invoke` to manage this repo. You don't need to use it, but it simplifies the workflow.
+## Set up the repo
+```shell
+git clone https://github.com/arcee-ai/arcee-python && cd arcee-python
+# optionally setup your virtual environment (recommended)
+python -m venv .venv && source .venv/bin/activate
+# install repo
+pip install invoke
+inv install
+```
+
+## Format, lint, test
+```shell
+inv format  # run black and ruff
+inv lint    # black check, ruff check, mypy
+inv test    # pytest
+```
+
+## Publishing
+We publish in this repo by creating a new release/tag in github. On release, a github action will 
+publish the `__version__` of arcee-py that is in `arcee/__init__.py`
+
+**So you need to increase that version before releasing, otherwise it will fail**
+
+### To create a new release
+1. Open a PR increasing the `__version__` of arcee-py. You can manually edit it or run `inv uv`
+2. Create a new release, with the name being the `__version__` of arcee-py
+
+### Manual release [not recommended]
+
+We do not recommend this. If you need to, please make the version number an alpha or beta release.<br>
+If you need to create a manual release, you can run `inv build && inv publish`

arcee/__init__.py

@@ -1,103 +1,12 @@
-__version__ = "0.0.9"
-import os
-import requests
-import json
-from arcee.dalm import DALM
-from arcee.dalm import check_model_status
-from arcee.config import ARCEE_API_KEY, ARCEE_API_URL, ARCEE_APP_URL, ARCEE_API_VERSION
-import time
-
-if ARCEE_API_KEY is None:
-    raise Exception(f"ARCEE_API_KEY must be in the environment. You can retrieve your API key from {ARCEE_APP_URL}")
-
-def upload_doc(context, doc_name, doc_text):
-    """
-    Upload a document to a context
-
-    Args:
-        context (str): The name of the context to upload to
-        doc_name (str): The name of the document
-        doc_text (str): The text of the document
-    """
-    doc = {
-        "name": doc_name,
-        "document": doc_text
-    }
-
-    headers = {
-        "X-Token": f"{ARCEE_API_KEY}",
-        "Content-Type": "application/json"
-    }
-
-    data = {
-        "context_name": context,
-        "documents": [doc]
-    }
-
-    response = requests.post(f"{ARCEE_API_URL}/{ARCEE_API_VERSION}/upload-context", headers=headers, data=json.dumps(data))
-
-    if response.status_code != 200:
-        raise Exception(f"Failed to upload example. Response: {response.text}")
-
-    return response.json()
-
-def upload_docs(context, docs):
-    """
-    Upload a list of documents to a context
+__version__ = "0.0.10"
 
-    Args:
-        context (str): The name of the context to upload to
-        docs (list): A list of dictionaries with keys "doc_name" and "doc_text"
-    """
-    doc_list = []
-    for doc in docs:
-        if "doc_name" not in doc.keys() or "doc_text" not in doc.keys():
-            raise Exception("Each document must have a doc_name and doc_text key")
 
-        doc_list.append({
-            "name": doc["doc_name"],
-            "document": doc["doc_text"]
-        })
-
-    headers = {
-        "X-Token": f"{ARCEE_API_KEY}",
-        "Content-Type": "application/json"
-    }
-
-    data = {
-        "context_name": context,
-        "documents": doc_list
-    }
-
-    response = requests.post(f"{ARCEE_API_URL}/{ARCEE_API_VERSION}/upload-context", headers=headers, data=json.dumps(data))
-
-    if response.status_code != 200:
-        raise Exception(f"Failed to upload example. Response: {response.text}")
-
-    return response.json()
-
-
-def train_dalm(name, context=None, instructions=None, generator="Command"):
-
-    endpoint = f"{ARCEE_API_URL}/{ARCEE_API_VERSION}/train-model"
-    data_to_send = {
-        "name": name,
-        "context": context,
-        "instructions": instructions,
-        "generator": generator
-    }
-
-    headers = {
-        "X-Token": f"{ARCEE_API_KEY}",
-        "Content-Type": "application/json"
-    }
+from arcee.api import get_dalm, train_dalm, upload_doc, upload_docs
+from arcee.config import ARCEE_API_KEY, ARCEE_APP_URL
+from arcee.dalm import DALM
 
-    response = requests.post(endpoint, data=json.dumps(data_to_send), headers=headers)
+if not ARCEE_API_KEY:
+    raise Exception(f"ARCEE_API_KEY must be in the environment. You can retrieve your API key from {ARCEE_APP_URL}")
 
-    if response.status_code != 201:
-        raise Exception(f"Failed to train model. Response: {response.text}")
-    else:
-        print("DALM model training started - view model status at {ARCEE_APP_URL}, then arcee.get_model(" + name + ")")
 
-def get_dalm(name):
-    return DALM(name)
+__all__ = ["upload_docs", "upload_doc", "train_dalm", "get_dalm", "DALM"]

arcee/api.py

@@ -0,0 +1,81 @@
+import json
+from typing import Optional
+
+import requests
+
+from arcee.config import ARCEE_API_KEY, ARCEE_API_URL, ARCEE_API_VERSION
+from arcee.dalm import DALM
+
+
+def upload_doc(context: str, doc_name: str, doc_text: str) -> dict[str, str]:
+    """
+    Upload a document to a context
+
+    Args:
+        context (str): The name of the context to upload to
+        doc_name (str): The name of the document
+        doc_text (str): The text of the document
+    """
+    doc = {"name": doc_name, "document": doc_text}
+
+    headers = {"X-Token": f"{ARCEE_API_KEY}", "Content-Type": "application/json"}
+
+    data = {"context_name": context, "documents": [doc]}
+
+    response = requests.post(
+        f"{ARCEE_API_URL}/{ARCEE_API_VERSION}/upload-context", headers=headers, data=json.dumps(data)
+    )
+
+    if response.status_code != 200:
+        raise Exception(f"Failed to upload example. Response: {response.text}")
+
+    return response.json()
+
+
+def upload_docs(context: str, docs: list[dict[str, str]]) -> dict[str, str]:
+    """
+    Upload a list of documents to a context
+
+    Args:
+        context (str): The name of the context to upload to
+        docs (list): A list of dictionaries with keys "doc_name" and "doc_text"
+    """
+    doc_list = []
+    for doc in docs:
+        if "doc_name" not in doc.keys() or "doc_text" not in doc.keys():
+            raise Exception("Each document must have a doc_name and doc_text key")
+
+        doc_list.append({"name": doc["doc_name"], "document": doc["doc_text"]})
+
+    headers = {"X-Token": f"{ARCEE_API_KEY}", "Content-Type": "application/json"}
+
+    data = {"context_name": context, "documents": doc_list}
+
+    response = requests.post(
+        f"{ARCEE_API_URL}/{ARCEE_API_VERSION}/upload-context", headers=headers, data=json.dumps(data)
+    )
+
+    if response.status_code != 200:
+        raise Exception(f"Failed to upload example. Response: {response.text}")
+
+    return response.json()
+
+
+def train_dalm(
+    name: str, context: Optional[str] = None, instructions: Optional[str] = None, generator: str = "Command"
+) -> None:
+    endpoint = f"{ARCEE_API_URL}/{ARCEE_API_VERSION}/train-model"
+    data_to_send = {"name": name, "context": context, "instructions": instructions, "generator": generator}
+
+    headers = {"X-Token": f"{ARCEE_API_KEY}", "Content-Type": "application/json"}
+
+    response = requests.post(endpoint, data=json.dumps(data_to_send), headers=headers)
+
+    if response.status_code != 201:
+        raise Exception(f"Failed to train model. Response: {response.text}")
+    else:
+        print("DALM model training started - view model status at {ARCEE_APP_URL}, then arcee.get_model(" + name + ")")
+
+
+def get_dalm(name: str) -> DALM:
+    return DALM(name)