| import langchain | |
| import os | |
| import openai | |
| from langchain.embeddings import OpenAIEmbeddings | |
| from langchain.vectorstores import Chroma | |
| from langchain import OpenAI, VectorDBQA | |
| import nltk | |
| from langchain.document_loaders import UnstructuredFileLoader | |
| from langchain.text_splitter import CharacterTextSplitter | |
| loader = UnstructuredFileLoader('RAJAGOPAL Thesis.txt') | |
| documents = loader.load() | |
| text_splitter = CharacterTextSplitter(chunk_size = 1000, chunk_overlap = 0) | |
| texts = text_splitter.split_documents(documents) | |
| openai.api_key = os.environ['OPENAI_API_KEY'] | |
| embeddings = OpenAIEmbeddings() | |
| doc_search = Chroma.from_documents(texts, embeddings) | |
| chain = VectorDBQA.from_chain_type(llm = OpenAI(), chain_type = "stuff", vectorstore = doc_search) | |
| def chat(input_text): | |
| return chain.run(input_text) | |
| import gradio as gr | |
| input_text = gr.inputs.Textbox(lines=7, label="Input") | |
| output_text = gr.outputs.Textbox(label="Output") | |
| gr.Interface( | |
| fn=chat, | |
| inputs=input_text, | |
| outputs=output_text, | |
| title="thesisGPT", | |
| flagging_enabled=False, | |
| description="A Conversational GPT based bot for exploring the thesis work done - AN AI-BASED FRAMEWORK AND DATA-DRIVEN METHODOLOGY FOR POST-PCR HIGH-RESOLUTION MELTING ANALYSIS.", | |
| theme="vertical", | |
| ).launch() |