File size: 4,436 Bytes
e5224e4 a474d08 e5224e4 63ca731 a89b188 f1fc1a8 a474d08 f1fc1a8 e5224e4 a8eb38b e5224e4 a1f2cae e5224e4 a1f2cae e5224e4 4fea8d8 e0dd3be a89b188 4fea8d8 5a2c7b1 a1f2cae 5a2c7b1 e5224e4 dcf49e5 a1f2cae dcf49e5 e5224e4 3879143 |
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 |
from sentence_transformers import SentenceTransformer
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.messages import AIMessage, HumanMessage
from langchain_chroma import Chroma
import gradio as gr
from huggingface_hub import InferenceClient
import os
import shutil
shutil.rmtree("/root/.cache", ignore_errors=True)
shutil.rmtree("/tmp", ignore_errors=True)
# Load environment variables
CHROMA_PATH = "chroma"
KEY = os.getenv("token")
# Hugging Face API setup
repo_id = "Qwen/Qwen2.5-7B-Instruct"
PROMPT_TEMPLATE = """
Answer the question based on the context provided. If no relevant information is found, state so.
Context:
{context}
Question:
{question}
Answer:
// Do not include the statement "Based on the provided context" in your answer. Start directly with the answer.
// If the user mentions that he does not want to know about these courses, ask him what topic he wants to learn about in the answer.
If you encounter a text message which is not related to the context, the bot must respond with "I don't have relevant information to answer that. Kindly ask queries related to free data science and machine learning courses on Analytics Vidhya."
"""
# Initialize the local embedding model
embedding_model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
class LocalEmbeddingFunction:
def embed_documents(self, texts):
# Generate embeddings for a list of texts
embeddings = embedding_model.encode(texts)
return embeddings.tolist() if hasattr(embeddings, 'tolist') else embeddings
def embed_query(self, query):
# Generate an embedding for a single query string
query_embedding = embedding_model.encode(query)
return query_embedding.tolist() if hasattr(query_embedding, 'tolist') else query_embedding
class LLM:
def generate_response(self, prompt):
client = InferenceClient(
provider="together",
api_key = KEY
)
completion = client.chat.completions.create(
model=repo_id,
messages=[
{
"role": "user",
"content": prompt
}
],
max_tokens=500,
temperature=0.8
)
return str(completion.choices[0].message.content)
def get_embedding_function():
return LocalEmbeddingFunction()
def get_chat_response(query, history):
# Retrieve embeddings from the Chroma DB
embedding_function = get_embedding_function()
db = Chroma(persist_directory=CHROMA_PATH, embedding_function=embedding_function)
# Search the DB
results = db.similarity_search_with_score(query, k=5)
context_text = "\n\n---\n\n".join([doc.page_content for doc, _score in results])
# Create prompt with context and query
prompt_template = ChatPromptTemplate.from_template(PROMPT_TEMPLATE)
prompt = prompt_template.format(context=context_text, question=query)
# Generate response using the LLM class and Hugging Face model
model = LLM()
response_text = model.generate_response(prompt)
# Update the history
history.append(AIMessage(content = response_text))
return response_text
# Gradio Interface
def predict(message, history):
# Initialize history if not provided
history_langchain_format = []
for msg in history:
if msg['role'] == "user":
history_langchain_format.append(HumanMessage(content=msg['content']))
elif msg['role'] == "assistant":
history_langchain_format.append(AIMessage(content=msg['content']))
history_langchain_format.append(HumanMessage(content=message))
# Get response from the model
response = get_chat_response(message, history_langchain_format)
return response
# Define the introductory content
intro_content = """
# Course Recommendation Bot
This bot helps you find **free courses related to python, data science and machine learning** available on [Analytics Vidhya](https://www.analyticsvidhya.com/).
You can ask any questions related to these courses.
For example:
- "What are the free courses on Python?"
- "Do you have any courses on data science?"
"""
# Build the Gradio interface
with gr.Blocks() as demo:
gr.Markdown(intro_content) # Display introductory content
chatbot = gr.ChatInterface(predict, type="messages") # Chat interface
demo.launch(share=False, ssr_mode=False)
|