Spaces:
Runtime error
Runtime error
File size: 14,505 Bytes
7d88a24 be980dd 722ecec 579282f fd10b6c 39dff4c 28b69ba be980dd adc6d8b d22abe6 3eb706b 7dc22ca c5fff41 56811e2 7dc22ca f86940b 7bd7744 c1f218b 7dc22ca 3eb706b c1f218b 74f3ed7 be980dd c1f218b be980dd 52bb2a3 be980dd 722ecec b67fe1a adc6d8b 722ecec 94ec186 adc6d8b 94ec186 ff4e34f 94ec186 ff4e34f 94ec186 ff4e34f 94ec186 ff4e34f 94ec186 ff4e34f 94ec186 adc6d8b 4d5d42b adc6d8b ff4e34f c6ddc86 3661992 28b69ba 4854a72 176b9ce 4854a72 176b9ce d354d71 32cbfb2 176b9ce d50b1d6 176b9ce 4854a72 176b9ce d354d71 32cbfb2 176b9ce 4854a72 bb31795 176b9ce 4854a72 176b9ce 4854a72 176b9ce 4854a72 f2e5be8 722ecec ff4e34f 722ecec e8d566d ff4e34f 269ecea ff4e34f e8d566d 4d5d42b 269ecea ff4e34f d22abe6 7c61b22 ff4e34f 722ecec ff4e34f e8d566d c1f218b e8d566d 68403cb 3eb706b |
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 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 |
# Welcome to Team Tonic's MultiMed
from gradio_client import Client
import os
import numpy as np
import base64
import gradio as gr
import requests
import json
import dotenv
from scipy.io.wavfile import write
import PIL
from openai import OpenAI
import time
dotenv.load_dotenv()
seamless_client = Client("facebook/seamless_m4t")
def process_speech(audio_input):
"""
processing sound using seamless_m4t
"""
time.sleep(2) # wait for the audio to be saved
print(f"audio : {audio_input}")
print(f"audio type : {type(audio_input)}")
try :
audio_name = f"{np.random.randint(0, 100)}.wav"
sr, data = audio_input
write(audio_name, sr, data.astype(np.int16))
audio_input = audio_name
except :
pass
out = seamless_client.predict(
"S2TT",
"file",
None,
audio_input, #audio_name
"",
"French",# source language
"English",# target language
api_name="/run",
)
out = out[1] # get the text
try :
return f"{out}"
except Exception as e :
return f"{e}"
def process_image(image) :
img_name = f"{np.random.randint(0, 100)}.jpg"
PIL.Image.fromarray(image.astype('uint8'), 'RGB').save(img_name)
image = open(img_name, "rb").read()
base64_image = base64_image = base64.b64encode(image).decode('utf-8')
openai_api_key = os.getenv('OPENAI_API_KEY')
# oai_org = os.getenv('OAI_ORG')
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {openai_api_key}"
}
payload = {
"model": "gpt-4-vision-preview",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What's in this image?"
},
{
"type": "image_url",
"image_url": {
"url": f"data:image/jpeg;base64,{base64_image}"
}
}
]
}
],
"max_tokens": 300
}
response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
try :
out = response.json()
out = out["choices"][0]["message"]["content"]
return out
except Exception as e :
return f"{e}"
def query_vectara(text):
user_message = text
# Read authentication parameters from the .env file
CUSTOMER_ID = os.getenv('CUSTOMER_ID')
CORPUS_ID = os.getenv('CORPUS_ID')
API_KEY = os.getenv('API_KEY')
# Define the headers
api_key_header = {
"customer-id": CUSTOMER_ID,
"x-api-key": API_KEY
}
# Define the request body in the structure provided in the example
request_body = {
"query": [
{
"query": user_message,
"queryContext": "",
"start": 1,
"numResults": 50,
"contextConfig": {
"charsBefore": 0,
"charsAfter": 0,
"sentencesBefore": 2,
"sentencesAfter": 2,
"startTag": "%START_SNIPPET%",
"endTag": "%END_SNIPPET%",
},
"rerankingConfig": {
"rerankerId": 272725718,
"mmrConfig": {
"diversityBias": 0.35
}
},
"corpusKey": [
{
"customerId": CUSTOMER_ID,
"corpusId": CORPUS_ID,
"semantics": 0,
"metadataFilter": "",
"lexicalInterpolationConfig": {
"lambda": 0
},
"dim": []
}
],
"summary": [
{
"maxSummarizedResults": 5,
"responseLang": "auto",
"summarizerPromptName": "vectara-summary-ext-v1.2.0"
}
]
}
]
}
# Make the API request using Gradio
response = requests.post(
"https://api.vectara.io/v1/query",
json=request_body, # Use json to automatically serialize the request body
verify=True,
headers=api_key_header
)
if response.status_code == 200:
query_data = response.json()
if query_data:
sources_info = []
# Extract the summary.
summary = query_data['responseSet'][0]['summary'][0]['text']
# Iterate over all response sets
for response_set in query_data.get('responseSet', []):
# Extract sources
# Limit to top 5 sources.
for source in response_set.get('response', [])[:5]:
source_metadata = source.get('metadata', [])
source_info = {}
for metadata in source_metadata:
metadata_name = metadata.get('name', '')
metadata_value = metadata.get('value', '')
if metadata_name == 'title':
source_info['title'] = metadata_value
elif metadata_name == 'author':
source_info['author'] = metadata_value
elif metadata_name == 'pageNumber':
source_info['page number'] = metadata_value
if source_info:
sources_info.append(source_info)
result = {"summary": summary, "sources": sources_info}
return f"{json.dumps(result, indent=2)}"
else:
return "No data found in the response."
else:
return f"Error: {response.status_code}"
def convert_to_markdown(vectara_response_json):
vectara_response = json.loads(vectara_response_json)
if vectara_response:
summary = vectara_response.get('summary', 'No summary available')
sources_info = vectara_response.get('sources', [])
# Format the summary as Markdown
markdown_summary = f'**Summary:** {summary}\n\n'
# Format the sources as a numbered list
markdown_sources = ""
for i, source_info in enumerate(sources_info):
author = source_info.get('author', 'Unknown author')
title = source_info.get('title', 'Unknown title')
page_number = source_info.get('page number', 'Unknown page number')
markdown_sources += f"{i+1}. {title} by {author}, Page {page_number}\n"
return f"{markdown_summary}**Sources:**\n{markdown_sources}"
else:
return "No data found in the response."
# Main function to handle the Gradio interface logic
def process_and_query(text=None):
try:
# augment the prompt before feeding it to vectara
text = "the user asks the following to his health adviser " + text
# If an image is provided, process it with OpenAI and use the response as the text query for Vectara
# if image is not None:
# text = process_image(image)
# return "**Summary:** "+text
# if audio is not None:
# text = process_speech(audio)
# # augment the prompt before feeding it to vectara
# text = "the user asks the following to his health adviser " + text
# Now, use the text (either provided by the user or obtained from OpenAI) to query Vectara
vectara_response_json = query_vectara(text)
markdown_output = convert_to_markdown(vectara_response_json)
client = OpenAI()
prompt ="Answer in the same language, write it better, more understandable and shorter:"
markdown_output_final = markdown_output
completion = client.chat.completions.create(
model="gpt-3.5-turbo",
messages=[
{"role": "system", "content": prompt},
{"role": "user", "content": markdown_output_final}
]
)
final_response= completion.choices[0].message.content
return final_response
except Exception as e:
return str(e)
# Define the Gradio interface
# iface = gr.Interface(
# fn=process_and_query,
# inputs=[
# gr.Textbox(label="Input Text"),
# gr.Image(label="Upload Image"),
# gr.Audio(label="talk in french",
# sources=["microphone"]),
# ],
# outputs=[gr.Markdown(label="Output Text")],
# title="👋🏻Welcome to ⚕🗣️😷MultiMed - Access Chat ⚕🗣️😷",
# description='''
# ### How To Use ⚕🗣️😷MultiMed⚕:
# #### 🗣️📝Interact with ⚕🗣️😷MultiMed⚕ in any language using audio or text!
# #### 🗣️📝 This is an educational and accessible conversational tool to improve wellness and sanitation in support of public health.
# #### 📚🌟💼 The knowledge base is composed of publicly available medical and health sources in multiple languages. We also used [Kelvalya/MedAware](https://huggingface.co/datasets/keivalya/MedQuad-MedicalQnADataset) that we processed and converted to HTML. The quality of the answers depends on the quality of the dataset, so if you want to see some data represented here, do [get in touch](https://discord.gg/GWpVpekp). You can also use 😷MultiMed⚕️ on your own data & in your own way by cloning this space. 🧬🔬🔍 Simply click here: <a style="display:inline-block" href="https://huggingface.co/spaces/TeamTonic/MultiMed?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a></h3>
# #### Join us : 🌟TeamTonic🌟 is always making cool demos! Join our active builder's🛠️community on 👻Discord: [Discord](https://discord.gg/GWpVpekp) On 🤗Huggingface: [TeamTonic](https://huggingface.co/TeamTonic) & [MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Polytonic](https://github.com/tonic-ai) & contribute to 🌟 [PolyGPT](https://github.com/tonic-ai/polygpt-alpha)"
# ''',
# theme='ParityError/Anime',
# examples=[
# ["What is the proper treatment for buccal herpes?"],
# ["Male, 40 presenting with swollen glands and a rash"],
# ["How does cellular metabolism work TCA cycle"],
# ["What special care must be provided to children with chicken pox?"],
# ["When and how often should I wash my hands ?"],
# ["بکل ہرپس کا صحیح علاج کیا ہے؟"],
# ["구강 헤르페스의 적절한 치료법은 무엇입니까?"],
# ["Je, ni matibabu gani sahihi kwa herpes ya buccal?"],
# ],
# )
welcome_message = """
# 👋🏻Welcome to ⚕🗣️😷MultiMed - Access Chat ⚕🗣️😷
### How To Use ⚕🗣️😷MultiMed⚕:
#### 🗣️📝Interact with ⚕🗣️😷MultiMed⚕ in any language using audio or text!
#### 🗣️📝 This is an educational and accessible conversational tool to improve wellness and sanitation in support of public health.
#### 📚🌟💼 The knowledge base is composed of publicly available medical and health sources in multiple languages. We also used [Kelvalya/MedAware](https://huggingface.co/datasets/keivalya/MedQuad-MedicalQnADataset) that we processed and converted to HTML. The quality of the answers depends on the quality of the dataset, so if you want to see some data represented here, do [get in touch](https://discord.gg/GWpVpekp). You can also use 😷MultiMed⚕️ on your own data & in your own way by cloning this space. 🧬🔬🔍 Simply click here: <a style="display:inline-block" href="https://huggingface.co/spaces/TeamTonic/MultiMed?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a></h3>
#### Join us : 🌟TeamTonic🌟 is always making cool demos! Join our active builder's🛠️community on 👻Discord: [Discord](https://discord.gg/GWpVpekp) On 🤗Huggingface: [TeamTonic](https://huggingface.co/TeamTonic) & [MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Polytonic](https://github.com/tonic-ai) & contribute to 🌟 [PolyGPT](https://github.com/tonic-ai/polygpt-alpha)"
"""
with gr.Blocks(theme='ParityError/Anime') as iface :
gr.Markdown(welcome_message)
with gr.Tab("text summarization"):
text_input = gr.Textbox(label="input text",lines=5)
text_output = gr.Markdown(label="output text")
text_button = gr.Button("process text")
with gr.Tab("image identification"):
image_input = gr.Image(label="upload image")
image_output = gr.Markdown(label="output text")
image_button = gr.Button("process image")
with gr.Tab("speech to text translation"):
audio_input = gr.Audio(label="talk in french",type="filepath",sources="microphone")
audio_output = gr.Markdown(label="output text")
audio_button = gr.Button("process audio")
text_button.click(process_and_query, inputs=text_input, outputs=text_output)
image_button.click(process_image, inputs=image_input, outputs=image_output)
audio_button.click(process_speech, inputs=audio_input, outputs=audio_output)
iface.queue().launch(show_error=True,debug=True)
|