File size: 2,943 Bytes
6e2b09a 0b6c3ef 6e2b09a f75a474 0b6c3ef 6e2b09a 0b6c3ef cc9711e 8ca775c cc9711e f75a474 cc9711e f75a474 |
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 |
import streamlit as st
from llama_index.core import VectorStoreIndex
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.core.node_parser import SentenceSplitter
from llama_index.core.ingestion import IngestionPipeline
import chromadb
from llama_index.vector_stores.chroma import ChromaVectorStore
from llama_index.llms.ollama import Ollama
from llama_index.llms.huggingface import HuggingFaceLLM
from llama_index.core import Settings
# Ustawienia strony
st.title("Aplikacja z LlamaIndex")
db = chromadb.PersistentClient(path="./abc")
chroma_collection = db.get_or_create_collection("pomoc_ukrainie")
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
# Utw贸rz pipeline do przetwarzania dokument贸w
pipeline = IngestionPipeline(
transformations=[
SentenceSplitter(),
embed_model,
],
vector_store=vector_store
)
# Utw贸rz indeks
index = VectorStoreIndex.from_vector_store(vector_store, embed_model=embed_model)
# Utw贸rz silnik zapyta艅
# huggingface
from transformers import AutoTokenizer
# Settings.tokenizer = AutoTokenizer.from_pretrained(
# "Qwen/Qwen2-7B-Instruct"
# )
# Load the correct tokenizer for Qwen/Qwen2-7B-Instruct
tokeni = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B")
llm = HuggingFaceLLM(model_name="Qwen/Qwen2-0.5B", tokenizer=tokeni)
# print(llm._tokenizer)
query_engine = index.as_query_engine(
llm=llm,
response_mode='compact')
# Store LLM generated responses
if "messages" not in st.session_state.keys():
st.session_state.messages = [{"role": "assistant", "content": "Zadaj mi pytanie..."}]
# Display chat messages
for message in st.session_state.messages:
with st.chat_message(message["role"]):
st.write(message["content"])
# User-provided prompt
if input := st.chat_input():
st.session_state.messages.append({"role": "user", "content": input})
with st.chat_message("user"):
st.write(input)
# Generate a new response if last message is not from assistant
if st.session_state.messages[-1]["role"] != "assistant":
with st.chat_message("assistant"):
with st.spinner("Czekaj, odpowied藕 jest generowana.."):
response = query_engine.query(input)
# Zbuduj tre艣膰 wiadomo艣ci z odpowiedzi膮 i score
content = str(response.response) # Upewnij si臋, 偶e response jest stringiem
if hasattr(response, 'source_nodes') and response.source_nodes: # Sprawd藕, czy source_nodes istnieje
# Dodaj score pierwszego w臋z艂a (je艣li istnieje)
content += f"\nScore: {response.source_nodes[0].score:.4f}" # Dodaj score
st.write(content) # Wy艣wietl ca艂膮 tre艣膰 w Streamlit
message = {"role": "assistant", "content": content} # Zapisz ca艂膮 tre艣膰 w wiadomo艣ci
st.session_state.messages.append(message) |