File size: 2,191 Bytes
f44db6c 690bb75 f44db6c 63b0d2d f44db6c f46ac02 f44db6c 1530ac8 47c116b db967aa 1530ac8 a6318fa 1530ac8 a6318fa f44db6c f46ac02 9264b57 f46ac02 a6318fa 1530ac8 f46ac02 1530ac8 f46ac02 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
import requests
import streamlit as st
import os
from huggingface_hub import InferenceClient
API_URL = 'https://qe55p8afio98s0u3.us-east-1.aws.endpoints.huggingface.cloud'
API_KEY = os.getenv('API_KEY')
headers = {
"Authorization": f"Bearer {API_KEY}",
"Content-Type": "application/json"
}
# Prompt Set of Examples:
prompt = f"Write instructions to teach anyone to write a discharge plan. List the entities, features and relationships to CCDA and FHIR objects in boldface."
def StreamLLMChatResponse(prompt):
endpoint_url = API_URL
hf_token = API_KEY
client = InferenceClient(endpoint_url, token=hf_token)
gen_kwargs = dict(
max_new_tokens=512,
top_k=30,
top_p=0.9,
temperature=0.2,
repetition_penalty=1.02,
stop_sequences=["\nUser:", "<|endoftext|>", "</s>"],
)
stream = client.text_generation(prompt, stream=True, details=True, **gen_kwargs)
report=[]
res_box = st.empty()
collected_chunks=[]
collected_messages=[]
for r in stream:
if r.token.special:
continue
if r.token.text in gen_kwargs["stop_sequences"]:
break
collected_chunks.append(r.token.text)
chunk_message = r.token.text
collected_messages.append(chunk_message)
try:
report.append(r.token.text)
if len(r.token.text) > 0:
result="".join(report).strip()
res_box.markdown(f'*{result}*')
except:
st.write(' ')
def query(payload):
response = requests.post(API_URL, headers=headers, json=payload)
st.markdown(response.json())
return response.json()
def get_output(prompt):
return query({"inputs": prompt})
def main():
st.title("Medical Llama Test Bench with Inference Endpoints Llama 7B")
prompt = f"Write instructions to teach anyone to write a discharge plan. List the entities, features and relationships to CCDA and FHIR objects in boldface."
example_input = st.text_input("Enter your example text:", value=prompt)
if st.button("Run Prompt With Dr Llama"):
StreamLLMChatResponse(example_input)
if __name__ == "__main__":
main() |