File size: 7,153 Bytes
c02b4bf 6113980 570c651 b26b0a3 c02b4bf 6113980 07026cb 2742bc2 02412d9 6113980 d3ae86a c02b4bf d3ae86a c02b4bf 7502cc2 c02b4bf cfc7235 c02b4bf a126020 c02b4bf 570c651 4dfdae4 570c651 c02b4bf 6c4b824 c02b4bf |
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 |
import chromadb
import os
import gradio as gr
import json
from huggingface_hub import InferenceClient
import gspread
from oauth2client.service_account import ServiceAccountCredentials
from datetime import datetime
from google.oauth2 import service_account
# Google Sheets setup
scope = ["https://spreadsheets.google.com/feeds", "https://www.googleapis.com/auth/drive"]
key1 = os.getenv("key1")
json_data={
"type": "service_account",
"project_id": "nestolechatbot",
"private_key_id": key1,
"private_key": "-----BEGIN PRIVATE KEY-----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\nNSpeJscWS3XTT3wXgbHil7rzIg==\n-----END PRIVATE KEY-----\n",
"client_email": "[email protected]",
"client_id": "107457262210035412036",
"auth_uri": "https://accounts.google.com/o/oauth2/auth",
"token_uri": "https://oauth2.googleapis.com/token",
"auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
"client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/nestoleservice%40nestolechatbot.iam.gserviceaccount.com",
"universe_domain": "googleapis.com"
}
creds = service_account.Credentials.from_service_account_info(json_data, scopes=scope)
#creds = ServiceAccountCredentials.from_json_keyfile_name('/home/user/app/chromaold/nestolechatbot-5fe2aa26cb52.json', scope)
client = gspread.authorize(creds)
sheet = client.open("nestolechatbot").sheet1 # Open the sheet
def save_to_sheet(date,name, message):
# Write user input to the Google Sheet
sheet.append_row([date,name, message])
return f"Thanks {name}, your message has been saved!"
path='/Users/thiloid/Desktop/LSKI/ole_nest/Chatbot/LLM/chromaTS'
if(os.path.exists(path)==False): path="/home/user/app/chromaTS"
print(path)
#path='chromaTS'
#settings = Settings(persist_directory=storage_path)
#client = chromadb.Client(settings=settings)
client = chromadb.PersistentClient(path=path)
print(client.heartbeat())
print(client.get_version())
print(client.list_collections())
from chromadb.utils import embedding_functions
default_ef = embedding_functions.DefaultEmbeddingFunction()
sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name="T-Systems-onsite/cross-en-de-roberta-sentence-transformer")#"VAGOsolutions/SauerkrautLM-Mixtral-8x7B-Instruct")
#instructor_ef = embedding_functions.InstructorEmbeddingFunction(model_name="hkunlp/instructor-large", device="cuda")
#print(str(client.list_collections()))
collection = client.get_collection(name="chromaTS", embedding_function=sentence_transformer_ef)
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
def format_prompt(message, history):
prompt = "" #"<s>"
#for user_prompt, bot_response in history:
# prompt += f"[INST] {user_prompt} [/INST]"
# prompt += f" {bot_response}</s> "
prompt += f"[INST] {message} [/INST]"
return prompt
def response(
prompt, history,temperature=0.9, max_new_tokens=500, top_p=0.95, repetition_penalty=1.0,
):
temperature = float(temperature)
if temperature < 1e-2: temperature = 1e-2
top_p = float(top_p)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=max_new_tokens,
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
seed=42,
)
addon=""
results=collection.query(
query_texts=[prompt],
n_results=60,
#where={"source": "google-docs"}
#where_document={"$contains":"search_string"}
)
#print("REsults")
#print(results)
#print("_____")
dists=["<br><small>(relevance: "+str(round((1-d)*100)/100)+";" for d in results['distances'][0]]
#sources=["source: "+s["source"]+")</small>" for s in results['metadatas'][0]]
results=results['documents'][0]
print("TEst")
print(results)
print("_____")
combination = zip(results,dists)
combination = [' '.join(triplets) for triplets in combination]
#print(str(prompt)+"\n\n"+str(combination))
if(len(results)>1):
addon=" Bitte berücksichtige bei deiner Antwort ausschießlich folgende Auszüge aus unserer Datenbank, sofern sie für die Antwort erforderlich sind. Beantworte die Frage knapp und präzise. Ignoriere unpassende Datenbank-Auszüge OHNE sie zu kommentieren, zu erwähnen oder aufzulisten:\n"+"\n".join(results)
system="Du bist ein deutschsprachiges KI-basiertes Studienberater Assistenzsystem, das zu jedem Anliegen möglichst geeignete Studieninformationen empfiehlt."+addon+"\n\nUser-Anliegen:"
formatted_prompt = format_prompt(system+"\n"+prompt,history)
stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
output = ""
for response in stream:
output += response.token.text
yield output
#output=output+"\n\n<br><details open><summary><strong>Sources</strong></summary><br><ul>"+ "".join(["<li>" + s + "</li>" for s in combination])+"</ul></details>"
# Get current date and time
now = str(datetime.now())
save_to_sheet(now,prompt, output)
yield output
gr.ChatInterface(response, chatbot=gr.Chatbot(value=[[None,"Herzlich willkommen! Ich bin Chätti ein KI-basiertes Studienassistenzsystem, das für jede Anfrage die am besten Studieninformationen empfiehlt.<br>Erzähle mir, was du gerne tust!"]],render_markdown=True),title="German Studyhelper Chätti").queue().launch(share=True) #False, server_name="0.0.0.0", server_port=7864)
print("Interface up and running!")
|