Spaces:
Runtime error
Runtime error
File size: 4,107 Bytes
eaa0108 3cc511b eaa0108 |
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 |
from llama_index.core import SimpleDirectoryReader
from llama_index.core.node_parser import SentenceSplitter
from llama_index.core import Settings
from llama_index.llms.openai import OpenAI
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.core import SummaryIndex, VectorStoreIndex
from llama_index.core.tools import QueryEngineTool
from llama_index.core.query_engine.router_query_engine import RouterQueryEngine
from llama_index.core.selectors import LLMSingleSelector
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.llms.groq import Groq
from llama_index.core import Settings
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
import os
from dotenv import load_dotenv
load_dotenv()
GROQ_API_KEY = os.getenv("GROQ_API_KEY")
embed_model= HuggingFaceEmbeddings(model_name="BAAI/bge-large-en-v1.5")
llm = Groq(model="llama3-70b-8192", api_key=GROQ_API_KEY)
Settings.llm = llm
Settings.embed_model = embed_model
from llama_index.core import SimpleDirectoryReader
documents = SimpleDirectoryReader("files").load_data()
from llama_index.core import VectorStoreIndex, StorageContext
from llama_index.vector_stores.qdrant import QdrantVectorStore
import qdrant_client
client = qdrant_client.QdrantClient(
location=":memory:",
)
vector_store = QdrantVectorStore(
collection_name = "paper",
client=client,
enable_hybrid=True,
batch_size=20,
)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
documents,
embed_model=embed_model,
storage_context=storage_context,
)
from llama_index.core.memory import ChatMemoryBuffer
memory = ChatMemoryBuffer.from_defaults(token_limit= 3000)
chat_engine = index.as_chat_engine(
chat_mode="context",
memory=memory,
system_prompt=(
"You are an AI assistant who answers the user questions"
),
)
def is_greeting(user_input):
greetings = ["hello", "hi", "hey", "good morning", "good afternoon", "good evening", "greetings"]
user_input_lower = user_input.lower().strip()
return any(greet in user_input_lower for greet in greetings)
def is_bye(user_input):
greetings = ["bye","thanks", "thank you", "thanks a lot", "bye bye", "have a good day"]
user_input_lower = user_input.lower().strip()
return any(greet in user_input_lower for greet in greetings)
import gradio as gr
def chat_with_ai(user_input, chat_history):
if is_greeting(str(user_input)):
response = 'hi,how can i help you?'
chat_history.append((user_input, response))
return chat_history, ""
if is_bye(str(user_input)):
response = "you're welcome"
chat_history.append((user_input, response))
return chat_history, ""
response = chat_engine.chat(user_input)
full_text = response.response
references = response.source_nodes
ref,pages = [],[]
for i in range(len(references)):
if references[i].metadata['file_name'] not in ref:
ref.append(references[i].metadata['file_name'])
pages.append(references[i].metadata['page_label'])
complete_response = str(full_text) + "\n\n" + "references:" + str(ref) + "\n\n" + "pages:" + str(pages)
if ref !=[] :
chat_history.append((user_input, complete_response))
ref = []
elif ref==[] :
chat_history.append((user_input,str(response)))
return chat_history, ""
def gradio_chatbot():
with gr.Blocks() as demo:
gr.Markdown("# Chat Interface for llama3.1_70B with Groq and llama_index")
chatbot = gr.Chatbot(label="llamaindex Chatbot")
user_input = gr.Textbox(
placeholder="Ask a question...", label="Enter your question"
)
submit_button = gr.Button("Send")
chat_history = gr.State([])
submit_button.click(chat_with_ai, inputs=[user_input, chat_history], outputs=[chatbot, user_input])
user_input.submit(chat_with_ai, inputs=[user_input, chat_history], outputs=[chatbot, user_input])
return demo
gradio_chatbot().launch(debug=True) |