import chromadb
import os
import gradio as gr
import json
from huggingface_hub import InferenceClient

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):
  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=10,
      #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]
    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>"
    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 BERUFENET-RAG-Interface to the Hugging Face Hub").queue().launch(share=True) #False, server_name="0.0.0.0", server_port=7864)
print("Interface up and running!")