New branch

.github/workflows/workflow.yml/workflow.yml

@@ -0,0 +1,7 @@
+steps:
+    - name: My step
+      env:
+        API_KEY: ${{ secrets.APIKEY }}
+      run: |
+        # You can use the secret as an environment variable in this step
+        echo "API key is $API_KEY"

Dockerfile

@@ -0,0 +1,37 @@
+#simple_server exoframe login https://exoframe.xf.mkrs.link -k /Users/fawaztarar/Documents/makers/key.pem
+
+
+
+# Imagine this file as a recipe for setting up a virtual computer.
+
+# Dockerfiles typically start with a 'base image'. There are loads of these
+# and you can find them at hub.docker.com.
+# We're going to use a base image for Python veresion 3.11
+FROM python:3.11
+
+# This base image contains essentially everything necessary for a 'virtual
+# computer'. It has a terminal, certain basic commands, and of course Python.
+
+# We run a command to install `pipenv`
+RUN pip install pipenv
+
+# We'll need our app's files in the container in order to be able to run them!
+# We copy them in from the current directory to the folder `/app` in
+# our virtual computer. Reminder `.` means 'the current directory'
+COPY . /app
+
+# We set the working directory for commands from this point on
+WORKDIR /app
+
+# We run `pipenv install` to install our project's dependencies. Since we've
+# copied in our `Pipfile`, `pipenv` will use that to get a list of dependencies.
+# We include a couple of extra options suitable for deployment.
+RUN pipenv install --system --deploy
+
+# At this point we've set up our virtual computer, but we've not _yet_ run our
+# application. And we're not going to! We're just setting up the container
+# so that it's ready to do so when we tell it.
+
+# So we're going to tell Docker here that when we _do_ want to run it, this is
+# what it should run:
+CMD ["python", "app.py"]

Pipfile

@@ -0,0 +1,11 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+
+[dev-packages]
+
+[requires]
+python_version = "3.11"

README.md

@@ -1,28 +1,48 @@
-# chatgpt-retrieval
+## Chatbot for makers.tech
+
+openAI chatgpt3 free tier integration
+Chatbot data from data files PDF, text
+chatbot data extraction from makers.tech
+
+
+## update Constants
+# Replace with your own OpenAI API Key https://platform.openai.com/account/api-keys
+# and rename this file to constants.py.
+#APIKEY =  "sk-<your key here>"
+
 
-Simple script to use ChatGPT on your own files.
 
-Here's the [YouTube Video](https://youtu.be/9AXP7tCI9PI).
 
 ## Installation
 
-Install [Langchain](https://github.com/hwchase17/langchain) and other required packages.
-```
-pip install langchain openai chromadb tiktoken unstructured
-```
-Modify `constants.py.default` to use your own [OpenAI API key](https://platform.openai.com/account/api-keys), and rename it to `constants.py`.
-
-Place your own data into `data/data.txt`.
-
-## Example usage
-Test reading `data/data.txt` file.
-```
-> python chatgpt.py "what is my dog's name"
-Your dog's name is Sunny.
-```
-
-Test reading `data/cat.pdf` file.
-```
-> python chatgpt.py "what is my cat's name"
-Your cat's name is Muffy.
-```
+1. pipenv install
+
+2. pinev shell
+
+3. pip install pytest
+
+
+3. pip install flask
+
+4. pip install beautifulsoup4
+
+    pip install requests beautifulsoup4
+
+
+5. pip install PyPDF2
+
+6. pip install scrapy
+
+7. pytest
+
+8. pip install aiofiles
+
+9. pip install elasticsearch
+
+10. psql CREATE DATABASE chatbot_db;
+
+11. pip install Flask-SQLAlchemy psycopg2-binary
+
+12. pip install pdfplumber
+
+

chatgpt.py

@@ -1,52 +1,91 @@
-import os
-import sys
 
+import os
 import openai
-from langchain.chains import ConversationalRetrievalChain, RetrievalQA
-from langchain.chat_models import ChatOpenAI
-from langchain.document_loaders import DirectoryLoader, TextLoader
-from langchain.embeddings import OpenAIEmbeddings
-from langchain.indexes import VectorstoreIndexCreator
-from langchain.indexes.vectorstore import VectorStoreIndexWrapper
-from langchain.llms import OpenAI
-from langchain.vectorstores import Chroma
-
-import constants
-
-os.environ["OPENAI_API_KEY"] = constants.APIKEY
-
-# Enable to save to disk & reuse the model (for repeated queries on the same data)
-PERSIST = False
-
-query = None
-if len(sys.argv) > 1:
-  query = sys.argv[1]
-
-if PERSIST and os.path.exists("persist"):
-  print("Reusing index...\n")
-  vectorstore = Chroma(persist_directory="persist", embedding_function=OpenAIEmbeddings())
-  index = VectorStoreIndexWrapper(vectorstore=vectorstore)
-else:
-  #loader = TextLoader("data/data.txt") # Use this line if you only need data.txt
-  loader = DirectoryLoader("data/")
-  if PERSIST:
-    index = VectorstoreIndexCreator(vectorstore_kwargs={"persist_directory":"persist"}).from_loaders([loader])
-  else:
-    index = VectorstoreIndexCreator().from_loaders([loader])
-
-chain = ConversationalRetrievalChain.from_llm(
-  llm=ChatOpenAI(model="gpt-3.5-turbo"),
-  retriever=index.vectorstore.as_retriever(search_kwargs={"k": 1}),
-)
-
-chat_history = []
-while True:
-  if not query:
-    query = input("Prompt: ")
-  if query in ['quit', 'q', 'exit']:
-    sys.exit()
-  result = chain({"question": query, "chat_history": chat_history})
-  print(result['answer'])
-
-  chat_history.append((query, result['answer']))
-  query = None
+import requests
+from flask import Flask, request, jsonify, render_template
+from flask import current_app
+import json
+from PyPDF2 import PdfReader
+from flask_sqlalchemy import SQLAlchemy
+import pdfplumber
+from bs4 import BeautifulSoup
+from lib.config import Config
+from lib.db_models import db
+from lib.db_models import ExtractedData
+from lib.db_models import create_app, db, store_data, query_data
+from lib.search import simple_search
+from flask import Flask
+from lib.config import Config
+from lib.db_models import db
+
+
+
+from flask import Flask
+from lib.db_models import db
+
+
+def create_app():
+    app = Flask(__name__)
+    app.config.from_object(Config)
+
+    # Initialize extensions with the app instance
+    db.init_app(app)
+
+    return app
+
+
+
+
+
+
+
+@app.route('/')
+def chatbot():
+    return render_template('ai_chatbot.html')
+
+@app.route('/query', methods=['POST'])
+def handle_query():
+    data_request = request.json
+    query = data_request.get('query')
+
+    if not query:
+        return jsonify({"error": "No query provided"}), 400
+
+    context = simple_search(query)
+
+    try:
+        response = openai.ChatCompletion.create(
+            model="gpt-3.5-turbo",
+            messages=[
+                {"role": "system", "content": "You are a helpful assistant."},
+                {"role": "user", "content": query},
+                {"role": "assistant", "content": context},
+            ]
+        )
+        answer = response.choices[0].message['content']
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+    return jsonify({"answer": answer})
+
+
+
+@app.route('/test_error')
+def test_error():
+    raise Exception('Test exception')
+
+
+if __name__ == '__main__':
+    app.run(debug=False, port=5001) # Set to False in production
+
+
+
+
+
+
+
+
+
+
+
+