Spaces:
Build error
Build error
File size: 3,209 Bytes
d9814cc 9597e6d ffcb62d e6958ab ffcb62d 452bc8e ffcb62d 0711684 ffcb62d d9814cc ffcb62d 452bc8e ffcb62d cdc433f |
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 |
from my_functions.save_response import save_response
from llama_index import (
SimpleDirectoryReader,
GPTListIndex,
GPTSimpleVectorIndex,
LLMPredictor,
PromptHelper,
ServiceContext,
)
from llama_index.node_parser import SimpleNodeParser
from langchain import OpenAI
import gradio as gr
import sys
import os
import os.path
import shutil
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
# Get the value of OPENAI_API_KEY from the environment
api_key = os.getenv("OPENAI_API_KEY")
# Use the API key in your code
os.environ["OPENAI_API_KEY"] = api_key
sys.path.append("/my_functions")
# Defining the parameters for the index
max_input_size = 4096
num_outputs = 1024
max_chunk_overlap = 20
prompt_helper = PromptHelper(
max_input_size,
num_outputs,
max_chunk_overlap,
)
llm_predictor = LLMPredictor(
llm=OpenAI(temperature=0.7, model_name="gpt-3.5-turbo", max_tokens=num_outputs)
)
service_context = ServiceContext.from_defaults(
llm_predictor=llm_predictor, prompt_helper=prompt_helper
)
def construct_index(directory_path):
if os.path.isfile("index.json"):
# Index file exists, so we'll load it and add new documents to it
index = GPTSimpleVectorIndex.load_from_disk(
"index.json", service_context=service_context
)
documents = SimpleDirectoryReader(directory_path).load_data()
for doc in documents:
index.insert(doc, service_context=service_context)
index.save_to_disk("index.json")
else:
# Index file doesn't exist, so we'll create a new index from scratch
documents = SimpleDirectoryReader(directory_path).load_data()
index = GPTSimpleVectorIndex.from_documents(
documents, service_context=service_context
)
index.save_to_disk("index.json")
# Define the paths to the source and destination folders
absolute_path = os.path.dirname(__file__)
src_folder = os.path.join(absolute_path, "docs/")
dest_folder = os.path.join(absolute_path, "indexed_documents/")
# Get a list of all the files in the source folder
files = os.listdir(src_folder)
# Move each file from the source folder to the destination folder,
# except for the "do_not_delete.txt" file
for file in files:
if file != "do_not_delete.txt":
src_path = os.path.join(src_folder, file)
dest_path = os.path.join(dest_folder, file)
shutil.move(src_path, dest_path)
return index
def chatbot(input_text):
index = GPTSimpleVectorIndex.load_from_disk(
"index.json", service_context=service_context
)
response = index.query(input_text, response_mode="default")
try:
save_response(input_text, response)
except Exception as e:
print("Error saving response:", e)
return response.response, response.get_formatted_sources()
iface = gr.Interface(
fn=chatbot,
inputs=gr.inputs.Textbox(lines=2, label="Enter your text"),
outputs=[gr.Textbox(lines=30, label="Output"), gr.Textbox(lines=4, label="Source")],
title="Custom-trained AI Chatbot",
)
index = construct_index("docs")
iface.launch()
|