Skip to content

feat: add support for custom inference api #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
martinchapman wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat: add support for custom inference api #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions .env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,3 @@
OPENPIPE_API_KEY=<APIKEY>
OPENPIPE_MODEL=openpipe:oncollama-v3-beta1
API_KEY=<APIKEY>
MODEL=openpipe:oncollama-v3-beta1
BASE_URL=<BASEURL>
7 changes: 4 additions & 3 deletions gui.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ class OpenPipeGUI:
def __init__(self):
self.api_key = None
self.model = None
self.base_url = None
self.connected = False

def parse_escape_sequences(self, text):
Expand All @@ -26,15 +27,15 @@ def initialise(self):
Initialise GUI, test API connection
"""
# for api keys
self.api_key, self.model = load_env_vars()
self.api_key, self.model, self.base_url = load_env_vars()

if not self.api_key or not self.model:
dpg.set_value("status_text", "Error: Missing API key or model in .env")
dpg.configure_item("status_indicator", default_value=False)
return

dpg.set_value("status_text", "Testing connection...")
success, message = test_connection(self.api_key, self.model)
success, message = test_connection(self.api_key, self.model, self.base_url)

self.connected = success
dpg.set_value("status_text", message)
Expand Down Expand Up @@ -67,7 +68,7 @@ def on_infer_clicked(self):
dpg.configure_item("infer_button", enabled=False)

# call API
success, result = call_openpipe_api(self.api_key, self.model, input_text)
success, result = call_openpipe_api(self.api_key, self.model, input_text, self.base_url)

dpg.set_value("output_text", result)
dpg.configure_item("infer_button", enabled=True)
Expand Down
20 changes: 10 additions & 10 deletions utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,21 +7,21 @@

"""
utils.py - supporting functions for backend operations (API, data processing)

Currently hard-coded to openpipe serverless deployment
Can refactor for additional LLM client compatibility (e.g. Bedrock)
"""

def load_env_vars():
load_dotenv()
api_key = os.getenv("OPENPIPE_API_KEY")
model = os.getenv("OPENPIPE_MODEL")
return api_key, model
api_key = os.getenv("API_KEY")
model = os.getenv("MODEL")
base_url = os.getenv("BASE_URL", None)
return api_key, model, base_url

def get_client(api_key, base_url=None):
return OpenAI(api_key=api_key, base_url=base_url) if base_url else OpenAI(api_key=api_key, openpipe={"api_key": api_key})

def test_connection(api_key, model):
def test_connection(api_key, model, base_url=None):
try:
client = OpenAI(openpipe={"api_key": api_key})
client = get_client(api_key, base_url)
client.chat.completions.create(
model=model,
messages=[{"role": "user", "content": "test"}],
Expand Down Expand Up @@ -50,9 +50,9 @@ def extract_output_json(text):
return text # or return original


def call_openpipe_api(api_key, model, user_text):
def call_openpipe_api(api_key, model, user_text, base_url=None):
try:
client = OpenAI(openpipe={"api_key": api_key})
client = get_client(api_key, base_url)
system_prompt = create_system_prompt('infer_prompt.txt')

completion = client.chat.completions.create(
Expand Down