Upload 6 files

.env

@@ -0,0 +1,3 @@
+GOOGLE_API_KEY=AIzaSyCxx1xZxh3LsIHD2M205dOAoMKC6IzatjI
+ANTHROPIC_API_KEY=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
+AURA_API_KEY=988584492fe87315ff6a4754be8613fa4b4fe87d

Data_Collection.ipynb

@@ -0,0 +1,326 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "GdqJu0iA0Qkm",
+        "outputId": "a1d4fdd0-36f5-42de-f4a3-31fa124a0fb3"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m850.5/850.5 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.8/77.8 kB\u001b[0m \u001b[31m7.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25h  Building wheel for google-search-results (setup.py) ... \u001b[?25l\u001b[?25hdone\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install --upgrade google-search-results --quiet"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "XEzTZ14602JJ"
+      },
+      "outputs": [],
+      "source": [
+        "import serpapi\n",
+        "import time\n",
+        "serpapi_key=\"your key\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "most_visited_countries = [\n",
+        "    \"France\", \"Spain\", \"United States\", \"China\", \"Italy\", \"United Kingdom\", \"Germany\", \"Mexico\", \"Thailand\", \"Turkey\",\n",
+        "    \"Austria\", \"Malaysia\", \"Russia\", \"Greece\", \"Japan\", \"Canada\", \"Portugal\", \"Saudi Arabia\", \"Australia\", \"Netherlands\",\n",
+        "    \"South Korea\", \"Egypt\", \"United Arab Emirates\", \"Singapore\", \"Indonesia\", \"India\", \"Vietnam\", \"Croatia\", \"Switzerland\",\n",
+        "    \"Poland\", \"South Africa\", \"Sweden\", \"Morocco\", \"Philippines\", \"Argentina\", \"Brazil\", \"Belgium\", \"Denmark\", \"Norway\",\n",
+        "    \"Peru\", \"Czech Republic\", \"Hungary\", \"Finland\", \"Ireland\", \"New Zealand\", \"Kenya\", \"Tanzania\", \"Israel\", \"Colombia\",\n",
+        "    \"Chile\", \"Iran\", \"Qatar\", \"Oman\", \"Ukraine\", \"Jordan\", \"Romania\", \"Kazakhstan\", \"Pakistan\", \"Bangladesh\", \"Nepal\",\n",
+        "    \"Bhutan\", \"Sri Lanka\", \"Myanmar\", \"Cambodia\", \"Laos\", \"Ethiopia\", \"Nigeria\", \"Kenya\", \"Uganda\", \"Rwanda\", \"Botswana\",\n",
+        "    \"Zimbabwe\", \"Namibia\", \"Zambia\", \"Tunisia\", \"Algeria\", \"Mauritius\", \"Mauritania\", \"Senegal\", \"Ghana\", \"Ivory Coast\",\n",
+        "    \"Cameroon\", \"Gabon\", \"Madagascar\", \"Seychelles\", \"Fiji\", \"Solomon Islands\", \"Vanuatu\", \"Samoa\", \"Tonga\", \"Kiribati\",\n",
+        "    \"Tuvalu\", \"Marshall Islands\", \"Palau\", \"Micronesia\", \"Nauru\", \"Cook Islands\", \"Niue\", \"Tokelau\", \"Comoros\", \"Maldives\",\n",
+        "    \"Cape Verde\", \"São Tomé and Príncipe\", \"Saint Kitts and Nevis\", \"Saint Lucia\", \"Saint Vincent and the Grenadines\",\n",
+        "    \"Dominica\", \"Antigua and Barbuda\", \"Barbados\", \"Grenada\", \"Belize\", \"Suriname\", \"Guyana\", \"Paraguay\"\n",
+        "]"
+      ],
+      "metadata": {
+        "id": "1AvPO_JMlwEo"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "hotels = []"
+      ],
+      "metadata": {
+        "id": "BUvNcOk8pGLu"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "oma2S1ai0QhM",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "a860bfc8-9949-489f-b6dd-7b2fa5ebb8da"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Total time for country: South Africa is 3.1462161540985107\n",
+            "Total time for country: Sweden is 4.135618448257446\n",
+            "Total time for country: Morocco is 3.870520830154419\n",
+            "Total time for country: Philippines is 3.1940598487854004\n",
+            "Total time for country: Argentina is 2.7493534088134766\n",
+            "Total time for country: Brazil is 3.4907991886138916\n",
+            "Total time for country: Belgium is 3.385352373123169\n",
+            "Total time for country: Denmark is 5.446274518966675\n",
+            "Total time for country: Norway is 2.5857763290405273\n",
+            "Total time for country: Peru is 3.4917497634887695\n",
+            "Total time for country: Czech Republic is 3.0693607330322266\n",
+            "Total time for country: Hungary is 3.3840672969818115\n",
+            "Total time for country: Finland is 3.126199722290039\n",
+            "Total time for country: Ireland is 7.195910692214966\n",
+            "Total time for country: New Zealand is 2.894592523574829\n",
+            "Total time for country: Kenya is 3.255056858062744\n",
+            "Total time for country: Tanzania is 2.524628162384033\n",
+            "Total time for country: Israel is 5.516220808029175\n",
+            "Total time for country: Colombia is 6.803558111190796\n",
+            "Total time for country: Chile is 5.247052907943726\n",
+            "Total time for country: Qatar is 6.248284339904785\n",
+            "Total time for country: Oman is 2.459817886352539\n",
+            "Total time for country: Ukraine is 2.5123510360717773\n",
+            "Total time for country: Jordan is 3.0355286598205566\n",
+            "Total time for country: Romania is 3.6406311988830566\n",
+            "Total time for country: Kazakhstan is 3.4437084197998047\n",
+            "Total time for country: Pakistan is 3.1847915649414062\n",
+            "Total time for country: Bangladesh is 4.030826807022095\n",
+            "Total time for country: Nepal is 2.4323649406433105\n",
+            "Total time for country: Bhutan is 2.3996434211730957\n",
+            "Total time for country: Sri Lanka is 4.682724952697754\n",
+            "Total time for country: Myanmar is 2.983024835586548\n",
+            "Total time for country: Cambodia is 2.5116500854492188\n",
+            "Total time for country: Laos is 2.3876218795776367\n",
+            "Total time for country: Ethiopia is 2.619466543197632\n",
+            "Total time for country: Nigeria is 3.833418846130371\n",
+            "Total time for country: Kenya is 0.1747727394104004\n",
+            "Total time for country: Uganda is 3.2861359119415283\n",
+            "Total time for country: Rwanda is 2.4624242782592773\n",
+            "Total time for country: Botswana is 2.4395322799682617\n",
+            "Total time for country: Zimbabwe is 2.4967572689056396\n",
+            "Total time for country: Namibia is 3.7246780395507812\n",
+            "Total time for country: Zambia is 2.8809072971343994\n",
+            "Total time for country: Tunisia is -0.0001838207244873047\n",
+            "Total time for country: Algeria is 3.2204713821411133\n",
+            "Total time for country: Mauritius is 4.015950918197632\n",
+            "Total time for country: Mauritania is 2.07582426071167\n",
+            "Total time for country: Senegal is 2.4191691875457764\n",
+            "Total time for country: Ghana is 1.9542012214660645\n",
+            "Total time for country: Ivory Coast is 3.2751688957214355\n",
+            "Total time for country: Cameroon is 2.822939872741699\n",
+            "Total time for country: Gabon is 2.2693305015563965\n",
+            "Total time for country: Madagascar is 3.0742127895355225\n",
+            "Total time for country: Seychelles is 2.3126015663146973\n",
+            "Total time for country: Fiji is 5.4941325187683105\n",
+            "Total time for country: Solomon Islands is 2.9408013820648193\n",
+            "Total time for country: Vanuatu is 3.2782294750213623\n",
+            "Total time for country: Samoa is 2.7137160301208496\n",
+            "Total time for country: Tonga is -0.0009427070617675781\n",
+            "Total time for country: Kiribati is -2.0623419284820557\n",
+            "Total time for country: Tuvalu is -9.399558782577515\n",
+            "Total time for country: Marshall Islands is -10.583814144134521\n",
+            "Total time for country: Palau is 4.033239841461182\n",
+            "Total time for country: Micronesia is -0.0008416175842285156\n",
+            "Total time for country: Nauru is -2.9765377044677734\n",
+            "Total time for country: Cook Islands is 2.2189862728118896\n",
+            "Total time for country: Niue is -0.0008838176727294922\n",
+            "Total time for country: Comoros is 2.1896681785583496\n",
+            "Total time for country: Maldives is 2.1256864070892334\n",
+            "Total time for country: Cape Verde is 2.577415943145752\n",
+            "Total time for country: São Tomé and Príncipe is 2.6751351356506348\n",
+            "Total time for country: Saint Kitts and Nevis is 2.8594794273376465\n",
+            "Total time for country: Saint Lucia is 2.7586190700531006\n",
+            "Total time for country: Saint Vincent and the Grenadines is 1.8319523334503174\n",
+            "Total time for country: Dominica is 2.2509264945983887\n",
+            "Total time for country: Antigua and Barbuda is 2.793400526046753\n",
+            "Total time for country: Barbados is 2.134657859802246\n",
+            "Total time for country: Grenada is 1.9456777572631836\n",
+            "Total time for country: Belize is 3.2146828174591064\n",
+            "Total time for country: Suriname is 1.9713115692138672\n",
+            "Total time for country: Guyana is 3.29117751121521\n",
+            "Total time for country: Paraguay is 3.483541250228882\n"
+          ]
+        }
+      ],
+      "source": [
+        "for country in most_visited_countries[:]:\n",
+        "  start = time.time()\n",
+        "  params = {\n",
+        "    \"engine\": \"google_hotels\",\n",
+        "    \"q\": f\"{country} Hotels\",\n",
+        "    \"check_in_date\": \"2024-03-16\",\n",
+        "    \"check_out_date\": \"2024-03-17\",\n",
+        "    \"adults\": \"2\",\n",
+        "    \"currency\": \"USD\",\n",
+        "    \"gl\": \"us\",\n",
+        "    \"hl\": \"en\",\n",
+        "    \"api_key\": serpapi_key\n",
+        "  }\n",
+        "  try:\n",
+        "    result = serpapi.search(params)\n",
+        "  except:\n",
+        "    result = serpapi.GoogleSearch(params)\n",
+        "  try:\n",
+        "    all_hotels = [] # append hotel deails\n",
+        "    # change this code to deep dive into dictionaries\n",
+        "    for idx in result.get_json()['properties']:\n",
+        "      if idx['type'] == \"hotel\":\n",
+        "        # Extract required data\n",
+        "        try:\n",
+        "          name = idx['name']\n",
+        "          check_in_time = idx['check_in_time']\n",
+        "          check_out_time = idx['check_out_time']\n",
+        "          lowest_rate_before_tax = idx['rate_per_night']['before_taxes_fees']\n",
+        "          lowest_rate_after_tax = idx['total_rate']['lowest']\n",
+        "          extracted_hotel_class = idx['extracted_hotel_class']\n",
+        "          overall_rating = idx['overall_rating']\n",
+        "          nearby_places_list = []\n",
+        "          nearby_places = idx['nearby_places']\n",
+        "          for place in nearby_places:\n",
+        "            place_name = place['name']\n",
+        "            nearby_places_list.append([place_name])\n",
+        "            for trans_med in place['transportations']:\n",
+        "              type_ = trans_med['type']\n",
+        "              duration = trans_med['duration']\n",
+        "              nearby_places_list[-1].append([type_, duration])\n",
+        "          ratings = []\n",
+        "          for dic in idx['ratings']:\n",
+        "            ratings.append(dic['count'])\n",
+        "          location_rating = idx['location_rating']\n",
+        "          reviews_breakdown = idx['reviews_breakdown']\n",
+        "          reviews_breakdown = []\n",
+        "          for dic in idx['reviews_breakdown']:\n",
+        "            if dic['name'] in [\"Service\", \"Nature\", \"Property\"]:\n",
+        "              positive_reviews = round((dic['positive'] / dic['total_mentioned'])*100, 0)\n",
+        "              negative_reviews = round((dic['negative'] / dic['total_mentioned'])*100, 0)\n",
+        "              reviews_breakdown.append((dic['name'], positive_reviews, negative_reviews))\n",
+        "          reviews_str = \"\"\n",
+        "          for review in reviews_breakdown:\n",
+        "            reviews_str += f\"{review[0]}: Positive Reviews -> {review[1]}% Negative Reviews -> {review[2]} \\n\"\n",
+        "          nearby_places_str = \"\"\n",
+        "          for place in nearby_places_list:\n",
+        "            # print(place)\n",
+        "            for idx, temp in enumerate(place):\n",
+        "              if idx == 0:\n",
+        "                temp_str = temp + \"  Distance:\"\n",
+        "                continue\n",
+        "              temp_str += f\" {place[idx][-1]} by {place[idx][0]}\"\n",
+        "            nearby_places_str += temp_str + \"\\n\"\n",
+        "          hotel_details = f\"\"\"\n",
+        "    Country : {country}\n",
+        "    Name: {name},\n",
+        "    Check in time: {check_in_time},\n",
+        "    Check out time : {check_out_time},\n",
+        "    Lowest rate (with tax) : {lowest_rate_after_tax},\n",
+        "    Lowest rate (without tax) : {lowest_rate_before_tax},\n",
+        "    Hotel Class : {extracted_hotel_class},\n",
+        "    Overall rating: {overall_rating}\n",
+        "    Reviews:\n",
+        "      5-start: {ratings[0]}, 4-start: {ratings[1]}, 3-start: {ratings[2]}, 2-start: {ratings[3]}, 1-start: {ratings[4]},\n",
+        "    Location Rating: {location_rating},\n",
+        "    Reviews Breakdown:\n",
+        "    {reviews_str}\n",
+        "    Nearby Places:\n",
+        "      {nearby_places_str}\n",
+        "            \"\"\"\n",
+        "          all_hotels.append(hotel_details)\n",
+        "          end = time.time()\n",
+        "        except Exception as e:\n",
+        "          continue\n",
+        "    hotels.append(all_hotels)\n",
+        "    print(f\"Total time for country: {country} is {end-start}\")\n",
+        "  except:\n",
+        "    continue\n",
+        "\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "hotels_str = \"\"\n",
+        "for country in hotels:\n",
+        "  for hotel in country:\n",
+        "    hotels_str += hotel.strip() + \"\\n\\n\"\n"
+      ],
+      "metadata": {
+        "id": "oEKIsk5qqq54"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import pickle\n",
+        "with open(\"all_hotels_list.pkl\", \"wb\") as file:\n",
+        "  pickle.dump(hotels, file)"
+      ],
+      "metadata": {
+        "id": "m8Yg0Cneshej"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "with open(\"all_hotels.txt\", \"w\") as file:\n",
+        "  file.write(hotels_str)"
+      ],
+      "metadata": {
+        "id": "k_VEcbCrr2z_"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

travel.py

@@ -0,0 +1,103 @@
+# import all necessary libraries
+import os
+import requests
+import streamlit as st
+from dotenv import load_dotenv
+import google.generativeai as genai
+from langchain_anthropic import ChatAnthropic
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_community.vectorstores.faiss import FAISS
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+
+# load api keys
+load_dotenv()
+
+# load models
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+chat = ChatAnthropic(temperature=0, anthropic_api_key=os.getenv("ANTHROPIC_API_KEY"), model_name="claude-3-opus-20240229")
+
+# Define the API endpoint
+url = "https://api.deepgram.com/v1/speak?model=aura-asteria-en"
+
+# Set your Deepgram API key
+
+# Define the headers
+api_key = os.getenv("AURA_API_KEY")
+headers = {
+    "Authorization": f"Token {api_key}",
+    "Content-Type": "application/json"
+}
+
+# Define the payload
+
+
+def get_embeddings(user_query):
+    embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")    
+    new_db = FAISS.load_local("faiss_index", embeddings)
+    docs = new_db.similarity_search(user_query)
+    return docs
+
+
+# Function to generate response based on user query
+def get_response(chat, prompt, user_query):
+    system = (
+    "You are world best travel advisor. Advice the user in best possible"
+    )
+    human = prompt
+    prompt = ChatPromptTemplate.from_messages([("system", system), ("human", human)])
+    docs = get_embeddings(user_query)
+    chain = prompt | chat
+    output = chain.invoke(
+        {
+            "context": docs,
+            "question" : user_query
+        }
+    )
+    return output.content
+
+# Streamlit app layout
+def main():
+    st.title("Claudestay")
+    
+    # api_key = st.text_input("Enter Anthropic API Key....")
+    # chat = ChatAnthropic(temperature=0, anthropic_api_key=api_key, model_name="claude-3-opus-20240229")
+
+    
+    prompt = """
+    Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
+    provided context just say, "answer is not available in the context", don't provide the wrong answer.
+    You must provide answer in markdown table format.\n\n
+    Context:\n {context}?\n
+    Question: \n{question}\n
+
+    Answer:
+"""
+
+    
+    # Input box for user query
+    user_query = st.text_input("Enter your travel query:")
+    
+    if st.button("Submit"):
+        with st.spinner("Fetching data..."):
+            text_response = get_response(chat, prompt, user_query)
+            payload = {
+            "text": text_response
+            }
+
+            # Make the POST request
+            st.markdown(f"**Response:** {text_response}")
+            # Check if the request was successful
+            response = requests.post(url, headers=headers, json=payload)
+            if response.status_code == 200:
+                # Save the response content to a file
+                with open("your_output_file.mp3", "wb") as f:
+                    f.write(response.content)
+                st.audio(response.content)
+                print("File saved successfully.")
+            else:
+                print(f"Error: {response.status_code} - {response.text}")
+                    
+
+if __name__ == "__main__":
+    main()

vectorstore.ipynb

@@ -0,0 +1,102 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Create Vector database"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "import google.generativeai as genai\n",
+    "from langchain_anthropic import ChatAnthropic\n",
+    "from langchain_community.vectorstores.faiss import FAISS\n",
+    "from langchain_google_genai import ChatGoogleGenerativeAI\n",
+    "from langchain_google_genai import GoogleGenerativeAIEmbeddings\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv()\n",
+    "genai.configure(api_key=os.getenv(\"GOOGLE_API_KEY\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_text_chunks(text):\n",
+    "    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)\n",
+    "    chunks = text_splitter.split_text(text)\n",
+    "    return chunks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_vector_store(text_chunks):\n",
+    "    embeddings = GoogleGenerativeAIEmbeddings(model = \"models/embedding-001\")\n",
+    "    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)\n",
+    "    vector_store.save_local(\"faiss_index\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"all_hotels.txt\", \"r\", encoding=\"utf8\") as file:\n",
+    "    text = file.read()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chunks = get_text_chunks(text)\n",
+    "get_vector_store(chunks)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}