Apply Ruff Corrections
This commit is contained in:
UncleCode
@@ -11,7 +11,9 @@ from groq import Groq
|
||||
# Import threadpools to run the crawl_url function in a separate thread
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
|
||||
client = AsyncOpenAI(base_url="https://api.groq.com/openai/v1", api_key=os.getenv("GROQ_API_KEY"))
|
||||
client = AsyncOpenAI(
|
||||
base_url="https://api.groq.com/openai/v1", api_key=os.getenv("GROQ_API_KEY")
|
||||
)
|
||||
|
||||
# Instrument the OpenAI client
|
||||
cl.instrument_openai()
|
||||
@@ -25,41 +27,39 @@ settings = {
|
||||
"presence_penalty": 0,
|
||||
}
|
||||
|
||||
|
||||
def extract_urls(text):
|
||||
url_pattern = re.compile(r'(https?://\S+)')
|
||||
url_pattern = re.compile(r"(https?://\S+)")
|
||||
return url_pattern.findall(text)
|
||||
|
||||
|
||||
def crawl_url(url):
|
||||
data = {
|
||||
"urls": [url],
|
||||
"include_raw_html": True,
|
||||
"word_count_threshold": 10,
|
||||
"extraction_strategy": "NoExtractionStrategy",
|
||||
"chunking_strategy": "RegexChunking"
|
||||
"chunking_strategy": "RegexChunking",
|
||||
}
|
||||
response = requests.post("https://crawl4ai.com/crawl", json=data)
|
||||
response_data = response.json()
|
||||
response_data = response_data['results'][0]
|
||||
return response_data['markdown']
|
||||
response_data = response_data["results"][0]
|
||||
return response_data["markdown"]
|
||||
|
||||
|
||||
@cl.on_chat_start
|
||||
async def on_chat_start():
|
||||
cl.user_session.set("session", {
|
||||
"history": [],
|
||||
"context": {}
|
||||
})
|
||||
await cl.Message(
|
||||
content="Welcome to the chat! How can I assist you today?"
|
||||
).send()
|
||||
cl.user_session.set("session", {"history": [], "context": {}})
|
||||
await cl.Message(content="Welcome to the chat! How can I assist you today?").send()
|
||||
|
||||
|
||||
@cl.on_message
|
||||
async def on_message(message: cl.Message):
|
||||
user_session = cl.user_session.get("session")
|
||||
|
||||
|
||||
# Extract URLs from the user's message
|
||||
urls = extract_urls(message.content)
|
||||
|
||||
|
||||
|
||||
futures = []
|
||||
with ThreadPoolExecutor() as executor:
|
||||
for url in urls:
|
||||
@@ -69,16 +69,9 @@ async def on_message(message: cl.Message):
|
||||
|
||||
for url, result in zip(urls, results):
|
||||
ref_number = f"REF_{len(user_session['context']) + 1}"
|
||||
user_session["context"][ref_number] = {
|
||||
"url": url,
|
||||
"content": result
|
||||
}
|
||||
user_session["context"][ref_number] = {"url": url, "content": result}
|
||||
|
||||
|
||||
user_session["history"].append({
|
||||
"role": "user",
|
||||
"content": message.content
|
||||
})
|
||||
user_session["history"].append({"role": "user", "content": message.content})
|
||||
|
||||
# Create a system message that includes the context
|
||||
context_messages = [
|
||||
@@ -95,26 +88,17 @@ async def on_message(message: cl.Message):
|
||||
"If not, there is no need to add a references section. "
|
||||
"At the end of your response, provide a reference section listing the URLs and their REF numbers only if sources from the appendices were used.\n\n"
|
||||
"\n\n".join(context_messages)
|
||||
)
|
||||
),
|
||||
}
|
||||
else:
|
||||
system_message = {
|
||||
"role": "system",
|
||||
"content": "You are a helpful assistant."
|
||||
}
|
||||
|
||||
system_message = {"role": "system", "content": "You are a helpful assistant."}
|
||||
|
||||
msg = cl.Message(content="")
|
||||
await msg.send()
|
||||
|
||||
# Get response from the LLM
|
||||
stream = await client.chat.completions.create(
|
||||
messages=[
|
||||
system_message,
|
||||
*user_session["history"]
|
||||
],
|
||||
stream=True,
|
||||
**settings
|
||||
messages=[system_message, *user_session["history"]], stream=True, **settings
|
||||
)
|
||||
|
||||
assistant_response = ""
|
||||
@@ -124,10 +108,7 @@ async def on_message(message: cl.Message):
|
||||
await msg.stream_token(token)
|
||||
|
||||
# Add assistant message to the history
|
||||
user_session["history"].append({
|
||||
"role": "assistant",
|
||||
"content": assistant_response
|
||||
})
|
||||
user_session["history"].append({"role": "assistant", "content": assistant_response})
|
||||
await msg.update()
|
||||
|
||||
# Append the reference section to the assistant's response
|
||||
@@ -154,10 +135,11 @@ async def on_audio_chunk(chunk: cl.AudioChunk):
|
||||
|
||||
pass
|
||||
|
||||
|
||||
@cl.step(type="tool")
|
||||
async def speech_to_text(audio_file):
|
||||
cli = Groq()
|
||||
|
||||
|
||||
response = await client.audio.transcriptions.create(
|
||||
model="whisper-large-v3", file=audio_file
|
||||
)
|
||||
@@ -172,24 +154,19 @@ async def on_audio_end(elements: list[ElementBased]):
|
||||
audio_buffer.seek(0) # Move the file pointer to the beginning
|
||||
audio_file = audio_buffer.read()
|
||||
audio_mime_type: str = cl.user_session.get("audio_mime_type")
|
||||
|
||||
|
||||
start_time = time.time()
|
||||
whisper_input = (audio_buffer.name, audio_file, audio_mime_type)
|
||||
transcription = await speech_to_text(whisper_input)
|
||||
end_time = time.time()
|
||||
print(f"Transcription took {end_time - start_time} seconds")
|
||||
|
||||
user_msg = cl.Message(
|
||||
author="You",
|
||||
type="user_message",
|
||||
content=transcription
|
||||
)
|
||||
|
||||
user_msg = cl.Message(author="You", type="user_message", content=transcription)
|
||||
await user_msg.send()
|
||||
await on_message(user_msg)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from chainlit.cli import run_chainlit
|
||||
|
||||
run_chainlit(__file__)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user