Upload folder using huggingface_hub

.dockerignore

@@ -0,0 +1,4 @@
+__pycache__/
+*.pyc
+*.pyo
+.git/

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+RAG-APP/data/fb.pdf filter=lfs diff=lfs merge=lfs -text

.github/workflows/update_space.yml

@@ -0,0 +1,28 @@
+name: Run Python script
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.9'
+
+    - name: Install Gradio
+      run: python -m pip install gradio
+
+    - name: Log in to Hugging Face
+      run: python -c 'import huggingface_hub; huggingface_hub.login(token="${{ secrets.hf_token }}")'
+
+    - name: Deploy to Spaces
+      run: gradio deploy

.gitignore

@@ -0,0 +1,5 @@
+/home/azureuser/rag-app/RAG-APP/myvenv
+myvenv
+.env
+main.py
+a.txt

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.12.3-slim
+
+WORKDIR /RAG-APP
+
+
+COPY requirements.txt .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 80
+
+CMD [ "python","app.py" ]

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

RAG-APP/data/fb.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee8b0f39e9fa375a5dcff70b2c87dc6b0284b0603258a6b59afaa95ff573761
+size 3536276

README.md

@@ -1,12 +1,45 @@
 ---
-title: QA Bot
-emoji: 📉
-colorFrom: gray
-colorTo: yellow
+title: QA-bot
+app_file: app.py
 sdk: gradio
 sdk_version: 4.44.0
-app_file: app.py
-pinned: false
 ---
+# PDF Question-Answering App using LangChain, Pinecone, and Mistral
+
+This project is a RAG app designed to perform question-answering (QA) on PDF documents. It uses the `LangChain` framework for embedding, `Pinecone` for vector storage, and the `mistral` language model for generating responses to user queries.
+
+## Features
+- **PDF Handling**: Load and split PDF files into manageable chunks for processing.
+- **Embeddings**: I am using the `SentenceTransformerEmbeddings` to create embeddings for document chunks.
+- **Vector Storage**: Pinecone is used to store document embeddings and efficiently retrieve relevant chunks based on user questions.
+- **LLM Integration**: I tried using LLMs locally using `Ollama`but due to lack of compute resources I used `mistral` for faster and better responses.
+- **Environment Variables**: Secrets like API keys are securely managed using `.env` files.
+
+## Requirements
+- Python 3.12
+- Run `pip install -r requirements.txt`
+- The following teck stack is used:
+  - `langchain`
+  - `pinecone` Make sure to sign up and create Pinecone API key 
+  - `Mistral API`
+  
+
+## Setup
+
+### 1. Clone the Repository
+```bash
+git clone https://github.com/m-umar-j/RAG-APP
+cd RAG-APP
+```
+### 2. install the requirements using 
+ ```bash
+ pip install -r requirements.txt`
+```
+### 3. create .env file in your root directory and add pinecone API key
+
+``` makefile
+PINECONE_API_KEY=your-pinecone-api-key
+```
+### 4. modify paths
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+`file_path = "/path/to/data.pdf"`

app.py

@@ -0,0 +1,75 @@
+import gradio as gr
+from langchain_community.embeddings import SentenceTransformerEmbeddings
+from langchain_community.vectorstores import Pinecone as LangchainPinecone
+from utilis import load_split_file, create_index, final_response
+from langchain_mistralai.chat_models import ChatMistralAI
+
+import os
+import shutil
+from dotenv import load_dotenv
+
+
+load_dotenv()
+PINECONE_API_KEY = os.getenv("PINECONE_API_KEY")
+MISTRAL_API_KEY = os.getenv("MISTRAL_API_KEY")
+
+
+
+embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+
+model = ChatMistralAI(mistral_api_key=MISTRAL_API_KEY)
+pinecone_index = "index"
+index_name = create_index(pinecone_index, PINECONE_API_KEY)
+
+def save_file(fileobj):
+    
+    upload_dir = "RAG-APP/data/"
+    if not os.path.exists(upload_dir):
+        os.makedirs(upload_dir)
+
+    # Save the file to the disk
+    file_path = os.path.join(upload_dir, os.path.basename(fileobj.name))
+    shutil.copyfile(fileobj.name, file_path)
+    
+    return file_path
+
+def process_pdf(fileobj):
+    file_path = save_file(fileobj)
+    docs = load_split_file(file_path)
+
+    
+    index = LangchainPinecone.from_documents(docs, embeddings, index_name=index_name)
+
+    return index, "File Uploaded Successfully"
+
+
+
+with gr.Blocks() as Iface:
+    file_input = gr.File(label="Upload PDF")  # This will give you the uploaded file's tempfile object
+
+    upload_file = gr.Button("Upload File")
+    index_state = gr.State()
+
+    message = gr.Textbox("Please wait while the file is processed!")
+    upload_file.click(fn = lambda file:
+                      process_pdf(file),
+                      inputs = file_input,
+                      outputs = [index_state, message])
+
+                        
+    question_input = gr.Textbox(label="Ask any question about your document")
+    
+    submit_button = gr.Button("Get Answer")
+
+    with gr.Row():
+        answer_output = gr.Textbox(label="Answer", scale=3)
+        matching_results = gr.Textbox(label="Reference", scale=1)
+    
+
+    submit_button.click(
+        fn=lambda index, q: final_response(index, q, model),
+        inputs=[index_state, question_input],
+        outputs=[answer_output, matching_results]
+    )
+
+Iface.launch(share=True)

notebook.ipynb

@@ -0,0 +1,213 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# PDF QA  RAG App"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Importing necessary libraries "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders import PyPDFLoader\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "\n",
+    "from langchain.prompts import PromptTemplate \n",
+    "from langchain_core.output_parsers import StrOutputParser \n",
+    "from operator import itemgetter\n",
+    "\n",
+    "from pinecone import Pinecone, ServerlessSpec"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Defining helper functions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_split_file(file_path):\n",
+    "    loader = PyPDFLoader(file_path)\n",
+    "    pages = loader.load_and_split()\n",
+    "\n",
+    "    \n",
+    "    text_splitter = RecursiveCharacterTextSplitter(chunk_size=200, chunk_overlap=10)\n",
+    "    docs = text_splitter.split_documents(pages)\n",
+    "\n",
+    "    return docs\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def create_index(index_name, PINECONE_API_KEY):\n",
+    "      \n",
+    "    pc = Pinecone(api_key=PINECONE_API_KEY)\n",
+    "\n",
+    "    if index_name in pc.list_indexes().names():\n",
+    "        pc.delete_index(index_name) # To avoid any conflicts in retrieval\n",
+    "    pc.create_index(\n",
+    "                name=index_name, \n",
+    "                dimension=384, \n",
+    "                metric='cosine',\n",
+    "                spec=ServerlessSpec(\n",
+    "                    cloud=\"aws\",\n",
+    "                    region=\"us-east-1\"\n",
+    "                )\n",
+    "            )\n",
+    "\n",
+    "    return index_name\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def final_response(index, question, model):\n",
+    "    retriever = index.as_retriever()\n",
+    "\n",
+    "    parser = StrOutputParser()\n",
+    "\n",
+    "    chain = model | parser \n",
+    "\n",
+    "    template = \"\"\"\n",
+    "    You must provide an answer based strictly on the context below. The answer is highly likely to be found within the given context, so analyze it thoroughly before responding. Only if there is absolutely no relevant information, respond with \"I don't know\".\n",
+    "\n",
+    "    Context: {context}\n",
+    "\n",
+    "    Question: {question}\n",
+    "    \"\"\"\n",
+    "\n",
+    "\n",
+    "    prompt = PromptTemplate.from_template(template)\n",
+    "    prompt.format(context=\"Here is some context\", question=\"Here is a question\")\n",
+    "\n",
+    "    chain = (\n",
+    "        {\n",
+    "            \"context\": itemgetter(\"question\") | retriever,\n",
+    "            \"question\": itemgetter(\"question\"),\n",
+    "        }\n",
+    "        | prompt\n",
+    "        | model\n",
+    "        | parser\n",
+    "    )\n",
+    "    matching_results=index.similarity_search(question,k=2)\n",
+    "\n",
+    "    return f\"Answer: {chain.invoke({'question': question})}\", matching_results\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import gradio as gr\n",
+    "from langchain_community.embeddings import SentenceTransformerEmbeddings\n",
+    "from langchain_community.vectorstores import Pinecone as LangchainPinecone\n",
+    "from utilis import load_split_file, create_index, final_response\n",
+    "from langchain_mistralai.chat_models import ChatMistralAI\n",
+    "\n",
+    "import os\n",
+    "import shutil\n",
+    "from dotenv import load_dotenv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv()\n",
+    "PINECONE_API_KEY = os.getenv(\"PINECONE_API_KEY\")\n",
+    "MISTRAL_API_KEY = os.getenv(\"MISTRAL_API_KEY\")\n",
+    "SAVE_DIR = \"/RAG-APP/data.pdf\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = SentenceTransformerEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
+    "\n",
+    "model = ChatMistralAI(mistral_api_key=MISTRAL_API_KEY)\n",
+    "pinecone_index = \"index\"\n",
+    "index_name = create_index(pinecone_index, PINECONE_API_KEY)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "file_path = \"data/last lesson.pdf\"\n",
+    "docs = load_split_file(file_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "index = LangchainPinecone.from_documents(docs, embeddings, index_name=index_name)\n",
+    "question = \"What data does google collects?\"\n",
+    "matching_results=index.similarity_search(question,k=2)\n",
+    "\n",
+    "answer = final_response(index, question, model)\n",
+    "\n",
+    "print(f\"{answer}\\n\\n{matching_results}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "myvenv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -0,0 +1,225 @@
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.0
+aiohttp==3.10.5
+aiohttp-cors==0.7.0
+aiosignal==1.3.1
+altair==5.4.1
+annotated-types==0.7.0
+anyio==4.4.0
+appdirs==1.4.4
+asttokens==2.4.1
+async-lru==2.0.4
+attrs==24.2.0
+beartype==0.15.0
+bleach==6.1.0
+blinker==1.8.2
+bokeh==3.5.2
+boto3==1.35.20
+botocore==1.35.20
+cachetools==5.5.0
+certifi==2024.8.30
+charset-normalizer==3.3.2
+click==8.1.7
+cohere==5.9.4
+comm==0.2.2
+contourpy==1.3.0
+cycler==0.12.1
+dataclasses-json==0.6.7
+debugpy==1.8.5
+decorator==5.1.1
+Deprecated==1.2.14
+diskcache==5.6.3
+distro==1.9.0
+docarray==0.40.0
+executing==2.1.0
+fastapi==0.115.0
+fastavro==1.9.7
+ffmpy==0.4.0
+filelock==3.16.0
+fonttools==4.53.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+geographiclib==2.0
+geopy==2.4.1
+gitdb==4.0.11
+GitPython==3.1.43
+google-ai-generativelanguage==0.6.9
+google-api-core==2.19.2
+google-api-python-client==2.145.0
+google-auth==2.34.0
+google-auth-httplib2==0.2.0
+google-cloud-bigquery==3.25.0
+google-cloud-core==2.4.1
+google-cloud-pubsub==2.23.1
+google-crc32c==1.6.0
+google-generativeai==0.8.1
+google-resumable-media==2.7.2
+googleapis-common-protos==1.65.0
+gradio==4.44.0
+gradio_client==1.3.0
+greenlet==3.1.0
+grpc-google-iam-v1==0.13.1
+grpcio==1.66.1
+grpcio-status==1.62.3
+h11==0.14.0
+h3==3.7.7
+httpcore==1.0.5
+httplib2==0.22.0
+httpx==0.27.2
+httpx-sse==0.4.0
+huggingface-hub==0.24.7
+idna==3.10
+importlib_metadata==8.4.0
+importlib_resources==6.4.5
+ipykernel==6.29.5
+ipython==8.27.0
+ipywidgets==8.1.5
+jedi==0.19.1
+Jinja2==3.1.4
+jiter==0.5.0
+jmespath==1.0.1
+joblib==1.4.2
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+jupyter_bokeh==4.0.5
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+jupyterlab_widgets==3.0.13
+kiwisolver==1.4.7
+langchain==0.3.0
+langchain-community==0.3.0
+langchain-core==0.3.0
+langchain-mistralai==0.2.0
+langchain-text-splitters==0.3.0
+langsmith==0.1.121
+linkify-it-py==2.0.3
+litellm==1.46.1
+Markdown==3.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.22.0
+matplotlib==3.9.2
+matplotlib-inline==0.1.7
+mdit-py-plugins==0.4.2
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+narwhals==1.8.1
+nest-asyncio==1.6.0
+networkx==3.3
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.45.1
+opentelemetry-api==1.27.0
+opentelemetry-exporter-otlp-proto-common==1.27.0
+opentelemetry-exporter-otlp-proto-grpc==1.27.0
+opentelemetry-proto==1.27.0
+opentelemetry-sdk==1.27.0
+opentelemetry-semantic-conventions==0.48b0
+orjson==3.10.7
+packaging==24.1
+pandas==2.2.2
+panel==1.5.0
+param==2.1.1
+parameterized==0.9.0
+parso==0.8.4
+pexpect==4.9.0
+pillow==10.4.0
+pinecone==5.3.0
+pinecone-plugin-inference==1.1.0
+pinecone-plugin-interface==0.0.7
+platformdirs==4.3.3
+prompt_toolkit==3.0.47
+proto-plus==1.24.0
+protobuf==4.25.4
+psutil==6.0.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyarrow==17.0.0
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pydantic==2.7.4
+pydantic-settings==2.5.2
+pydantic_core==2.18.4
+pydeck==0.9.1
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.4
+pypdf==4.3.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+python-sat==1.8.dev13
+pytz==2024.2
+pyviz_comms==3.0.3
+PyYAML==6.0.2
+pyzmq==26.2.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+rsa==4.9
+ruff==0.6.6
+s3transfer==0.10.2
+safetensors==0.4.5
+scikit-learn==1.5.2
+scipy==1.14.1
+semantic-version==2.10.0
+sentence-transformers==3.1.0
+setuptools==75.1.0
+shapely==2.0.6
+shellingham==1.5.4
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+SQLAlchemy==2.0.35
+sqlglot==10.6.1
+stack-data==0.6.3
+starlette==0.38.5
+sympy==1.13.2
+tenacity==8.5.0
+threadpoolctl==3.5.0
+tiktoken==0.7.0
+tokenizers==0.19.1
+toml==0.10.2
+tomlkit==0.12.0
+torch==2.4.1
+tornado==6.4.1
+tqdm==4.66.5
+traitlets==5.14.3
+transformers==4.44.2
+triton==3.0.0
+typer==0.12.5
+types-requests==2.32.0.20240914
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.1
+uc-micro-py==1.0.3
+uritemplate==4.1.1
+urllib3==2.2.3
+uvicorn==0.30.6
+watchdog==4.0.2
+wcwidth==0.2.13
+webencodings==0.5.1
+websockets==12.0
+widgetsnbextension==4.0.13
+wrapt==1.16.0
+xyzservices==2024.9.0
+yarl==1.11.1
+zipp==3.20.2

utilis.py

@@ -0,0 +1,76 @@
+from langchain_community.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+from langchain.prompts import PromptTemplate 
+from langchain_core.output_parsers import StrOutputParser 
+from operator import itemgetter
+
+from pinecone import Pinecone, ServerlessSpec
+
+
+
+def load_split_file(file_path):
+    loader = PyPDFLoader(file_path)
+    pages = loader.load_and_split()
+
+    
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=200, chunk_overlap=10)
+    docs = text_splitter.split_documents(pages)
+
+    return docs
+
+
+def create_index(index_name, PINECONE_API_KEY):
+      
+    pc = Pinecone(api_key=PINECONE_API_KEY)
+
+    if index_name in pc.list_indexes().names():
+        pc.delete_index(index_name) # To avoid any conflicts in retrieval
+    pc.create_index(
+                name=index_name, 
+                dimension=384, 
+                metric='cosine',
+                spec=ServerlessSpec(
+                    cloud="aws",
+                    region="us-east-1"
+                )
+            )
+
+    return index_name
+
+
+def final_response(index, question, model):
+    retriever = index.as_retriever()
+
+    parser = StrOutputParser()
+
+    chain = model | parser 
+
+    template = """
+    You must provide an answer based strictly on the context below. 
+    The answer is highly likely to be found within the given context, so analyze it thoroughly before responding. 
+    Only if there is absolutely no relevant information, respond with "I don't know".
+    Do not make things up.
+
+    Context: {context}
+
+    Question: {question}
+    """
+
+
+    prompt = PromptTemplate.from_template(template)
+    prompt.format(context="Here is some context", question="Here is a question")
+
+    chain = (
+        {
+            "context": itemgetter("question") | retriever,
+            "question": itemgetter("question"),
+        }
+        | prompt
+        | model
+        | parser
+    )
+    matching_results=index.similarity_search(question,k=2)
+
+    return f"Answer: {chain.invoke({'question': question})}", matching_results
+