apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-06-26 15:39:40 +02:00
Code Issues Projects Releases Packages Wiki Activity

lint + formating with black (#158)

Browse source 
* lint + formating with black

* add black as pre commit
This commit is contained in:
Co Tran 2024-10-09 11:25:07 -07:00 • committed by GitHub
parent 498e7f9724
commit 5c4a6bc8ff
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
22 changed files with 581 additions and 295 deletions
Download patch file Download diff file Expand all files Collapse all files

69
chatbot_ui/app/run.py
View file

@ -7,47 +7,53 @@ from dotenv import load_dotenv
load_dotenv()
OPENAI_API_KEY=os.getenv("OPENAI_API_KEY")
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
MISTRAL_API_KEY = os.getenv("MISTRAL_API_KEY")
CHAT_COMPLETION_ENDPOINT = os.getenv("CHAT_COMPLETION_ENDPOINT")
MODEL_NAME = os.getenv("MODEL_NAME", "gpt-3.5-turbo")
ARCH_STATE_HEADER = 'x-arch-state'
ARCH_STATE_HEADER = "x-arch-state"
log.info("CHAT_COMPLETION_ENDPOINT: ", CHAT_COMPLETION_ENDPOINT)
client = OpenAI(api_key=OPENAI_API_KEY, base_url=CHAT_COMPLETION_ENDPOINT, http_client=DefaultHttpxClient(headers={"accept-encoding": "*"}))
client = OpenAI(
api_key=OPENAI_API_KEY,
base_url=CHAT_COMPLETION_ENDPOINT,
http_client=DefaultHttpxClient(headers={"accept-encoding": "*"}),
)
def predict(message, state):
if 'history' not in state:
state['history'] = []
if "history" not in state:
state["history"] = []
history = state.get("history")
history.append({"role": "user", "content": message})
log.info("history: ", history)
# Custom headers
custom_headers = {
'x-arch-openai-api-key': f"{OPENAI_API_KEY}",
'x-arch-mistral-api-key': f"{MISTRAL_API_KEY}",
'x-arch-deterministic-provider': 'openai',
"x-arch-openai-api-key": f"{OPENAI_API_KEY}",
"x-arch-mistral-api-key": f"{MISTRAL_API_KEY}",
"x-arch-deterministic-provider": "openai",
}
metadata = None
if 'arch_state' in state:
metadata = {ARCH_STATE_HEADER: state['arch_state']}
if "arch_state" in state:
metadata = {ARCH_STATE_HEADER: state["arch_state"]}
try:
raw_response = client.chat.completions.with_raw_response.create(model=MODEL_NAME,
messages = history,
temperature=1.0,
metadata=metadata,
extra_headers=custom_headers
)
raw_response = client.chat.completions.with_raw_response.create(
model=MODEL_NAME,
messages=history,
temperature=1.0,
metadata=metadata,
extra_headers=custom_headers,
)
except Exception as e:
log.info(e)
# remove last user message in case of exception
history.pop()
log.info("Error calling gateway API: {}".format(e.message))
raise gr.Error("Error calling gateway API: {}".format(e.message))
log.info(e)
# remove last user message in case of exception
history.pop()
log.info("Error calling gateway API: {}".format(e.message))
raise gr.Error("Error calling gateway API: {}".format(e.message))
log.info("raw_response: ", raw_response.text)
response = raw_response.parse()
@ -57,24 +63,33 @@ def predict(message, state):
response_json = json.loads(raw_response.text)
arch_state = None
if response_json:
metadata = response_json.get('metadata', {})
if metadata:
arch_state = metadata.get(ARCH_STATE_HEADER, None)
metadata = response_json.get("metadata", {})
if metadata:
arch_state = metadata.get(ARCH_STATE_HEADER, None)
if arch_state:
state['arch_state'] = arch_state
state["arch_state"] = arch_state
content = response.choices[0].message.content
history.append({"role": "assistant", "content": content, "model": response.model})
messages = [(history[i]["content"], history[i+1]["content"]) for i in range(0, len(history)-1, 2)]
messages = [
(history[i]["content"], history[i + 1]["content"])
for i in range(0, len(history) - 1, 2)
]
return messages, state
with gr.Blocks(fill_height=True, css="footer {visibility: hidden}") as demo:
print("Starting Demo...")
chatbot = gr.Chatbot(label="Arch Chatbot", scale=1)
state = gr.State({})
with gr.Row():
txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter", scale=1, autofocus=True)
txt = gr.Textbox(
show_label=False,
placeholder="Enter text and press enter",
scale=1,
autofocus=True,
)
txt.submit(predict, [txt, state], [chatbot, state])

24
chatbot_ui/app/run_stream.py
View file

@ -5,26 +5,32 @@ from openai import OpenAI
import gradio as gr
api_key = os.getenv("OPENAI_API_KEY")
CHAT_COMPLETION_ENDPOINT = os.getenv("CHAT_COMPLETION_ENDPOINT", "https://api.openai.com/v1")
CHAT_COMPLETION_ENDPOINT = os.getenv(
"CHAT_COMPLETION_ENDPOINT", "https://api.openai.com/v1"
)
client = OpenAI(api_key=api_key, base_url=CHAT_COMPLETION_ENDPOINT)
def predict(message, history):
history_openai_format = []
for human, assistant in history:
history_openai_format.append({"role": "user", "content": human })
history_openai_format.append({"role": "assistant", "content":assistant})
history_openai_format.append({"role": "user", "content": human})
history_openai_format.append({"role": "assistant", "content": assistant})
history_openai_format.append({"role": "user", "content": message})
response = client.chat.completions.create(model='gpt-3.5-turbo',
messages= history_openai_format,
temperature=1.0,
stream=True)
response = client.chat.completions.create(
model="gpt-3.5-turbo",
messages=history_openai_format,
temperature=1.0,
stream=True,
)
partial_message = ""
for chunk in response:
if chunk.choices[0].delta.content is not None:
partial_message = partial_message + chunk.choices[0].delta.content
yield partial_message
partial_message = partial_message + chunk.choices[0].delta.content
yield partial_message
gr.ChatInterface(predict).launch(server_name="0.0.0.0", server_port=8081)