first version with emotions

.gitignore

@@ -0,0 +1,161 @@
+disney-lyrics/
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

app.py

@@ -0,0 +1,70 @@
+from pathlib import Path
+
+import streamlit as st
+from dotenv import load_dotenv
+from langchain.chains import LLMChain
+from langchain.prompts import PromptTemplate
+
+load_dotenv()
+import os
+
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings.openai import OpenAIEmbeddings
+
+from data import load_db
+from names import DATASET_ID, MODEL_ID
+
+@st.cache_resource
+def init():
+    embeddings = OpenAIEmbeddings(model=MODEL_ID)
+    dataset_path = f"hub://{os.environ['ACTIVELOOP_ORG_ID']}/{DATASET_ID}"
+
+    db = load_db(
+        dataset_path,
+        embedding_function=embeddings,
+        token=os.environ["ACTIVELOOP_TOKEN"],
+        org_id=os.environ["ACTIVELOOP_ORG_ID"],
+        read_only=True,
+    )
+
+    prompt = PromptTemplate(
+        input_variables=["content"],
+        template=Path("prompts/bot.prompt").read_text(),
+    )
+
+    llm = ChatOpenAI(temperature=0.7)
+
+    chain = LLMChain(llm=llm, prompt=prompt)
+
+    return db, chain
+
+db, chain = init()
+
+st.title("Disney song for you")
+
+text_input = st.text_input(
+    label="How are you feeling today?",
+    placeholder="I am ready to rock and rool!",
+)
+
+clicked = st.button("Click me")
+placeholder_emotions = st.empty()
+placeholder = st.empty()
+
+def get_emotions(user_input):
+    emotions = chain.run(content=user_input)
+    print(f"Emotions: {emotions}")
+    matches = db.similarity_search_with_score(emotions, distance_metric="cos")
+    print(matches)
+    doc, score = matches[0]
+    iframes_html = ""
+    with placeholder_emotions:
+        st.write(emotions)
+    with placeholder:
+        embed_url = doc.metadata["embed_url"]
+        iframe_html = f'<iframe src="{embed_url}" style="border:0"> </iframe>'
+        st.components.v1.html(f"<div style='display:flex;flex-direction:column'>{iframe_html}</div>")
+
+
+if clicked:
+    get_emotions(text_input)

data.py

@@ -1,66 +1,48 @@
+from dotenv import load_dotenv
 
-# def get_lyrics_url_from_website():
-#     # https://www.disneyclips.com/lyrics/
+load_dotenv()
+import json
+import os
 
-import aiohttp
-import asyncio
-from bs4 import BeautifulSoup
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.llms import OpenAI
+from langchain.vectorstores import DeepLake
 
-from typing import List, TypedDict, Tuple, Optional
+from names import DATASET_ID, MODEL_ID
 
-class Lyric(TypedDict):
-    name: str 
-    text: str
 
-class Movie(TypedDict):
-    title: str 
-    lyrics: List[Lyric]
+def create_db(dataset_path: str, json_filepath: str) -> DeepLake:
+    with open(json_filepath, "r") as f:
+        data = json.load(f)
 
+    texts = []
+    metadatas = []
 
-URL = "https://www.disneyclips.com/lyrics/"
+    for movie, lyrics in data.items():
+        for lyric in lyrics:
+            texts.append(lyric["text"])
+            metadatas.append(
+                {
+                    "movie": movie,
+                    "name": lyric["name"],
+                    "embed_url": lyric["embed_url"],
+                }
+            )
 
+    embeddings = OpenAIEmbeddings(model=MODEL_ID)
 
-async def get_lyrics_urls_from_movie_url(url: str, session: aiohttp.ClientSession) -> Optional[Tuple[str, str]]:
-    async with session.get(url) as response:
-        html = await response.text()
-        soup = BeautifulSoup(html, 'html.parser')
-        table = soup.find('table', {'class': 'songs'})
-        names_and_urls = None
-        if table:
-            links = table.find_all('a')
-            names_and_urls = []
-            for link in links:
-                names_and_urls.append((link.text,  f"{URL}/{link.get('href')}"))
-        return names_and_urls
+    db = DeepLake.from_texts(
+        texts, embeddings, metadatas=metadatas, dataset_path=dataset_path
+    )
 
-async def get_lyric_from_lyric_url(url: str, name: str, session: aiohttp.ClientSession) -> Lyric:
-    async with session.get(url) as response:
-        html = await response.text()
-        soup = BeautifulSoup(html, 'html.parser')
-        div = soup.find('div', {'id': 'cnt'}).find('div', {'class': 'main'})
-        paragraphs = div.find_all('p')
-        text = ""
-        for p in paragraphs:
-            text += p.text
-        return text
+    return db
 
 
+def load_db(dataset_path: str, *args, **kwargs) -> DeepLake:
+    db = DeepLake(dataset_path, *args, **kwargs)
+    return db
 
-async def get_movie_names_and_urls(session: aiohttp.ClientSession) -> List[Tuple[str, str]]:
-    async with session.get(URL) as response:
-        html = await response.text()
-        soup = BeautifulSoup(html, 'html.parser')
-        links = soup.find('div', {'id': 'cnt'}).find('div', {'class': 'main'}).find_all('a')
-        movie_names_and_urls = [(link.text, f"{URL}/{link.get('href')}") for link in links]
-        return movie_names_and_urls
-       
 
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        names_and_urls = await get_movie_names_and_urls(session)
-        data = await asyncio.gather(*[asyncio.create_task(get_lyrics_urls_from_movie_url(names, url, session)) for (names, url) in names_and_urls])
-
-loop = asyncio.get_event_loop()
-loop.run_until_complete(main())
+if __name__ == "__main__":
+    dataset_path = f"hub://{os.environ['ACTIVELOOP_ORG_ID']}/{DATASET_ID}"
+    create_db(dataset_path, "data/lyrics_with_spotify_url.json")

data/lyrics_with_spotify_url_and_summary.json

@@ -0,0 +1 @@
+{"friend like me": {"summary": "SUMMARY: The song is about the power of friendship and the willingness to help others, with a focus on the magical abilities of the genie and the endless possibilities that come with his assistance.", "embed_url": "https://open.spotify.com/embed/track/5f2TWu6R2YYCJtLQ0fP78H?utm_source=generator"}, "arabian nights": {"summary": "SUMMARY: The song evokes a sense of adventure and exoticism, with themes of home, heat, and the allure of Arabian nights.", "embed_url": "https://open.spotify.com/embed/track/0CKmN3Wwk8W4zjU0pqq2cv?utm_source=generator"}, "a whole new world": {"summary": "SUMMARY: The song is about the excitement and wonder of discovering a new world with someone you love, and the feeling of limitless possibilities that come with it.", "embed_url": "https://open.spotify.com/embed/track/1hwdPQtFHISvZ9SXMkNrIK?utm_source=generator"}, "one jump ahead": {"summary": "SUMMARY: Aladdin sings about his struggles as a street rat, constantly having to stay one step ahead of the law and society's expectations, while relying on his friendship with Abu to survive.", "embed_url": "https://open.spotify.com/embed/track/4wN8Ov3kPZdkJ8XcYxYUGz?utm_source=generator"}}

names.py

@@ -0,0 +1,2 @@
+MODEL_ID = "text-embedding-ada-002"
+DATASET_ID = "disney-lyrics"

playground.py

@@ -0,0 +1,60 @@
+from dotenv import load_dotenv
+
+load_dotenv()
+import json
+import os
+from pathlib import Path
+
+import deeplake
+import numpy as np
+import openai
+
+# https://www.disneyclips.com/lyrics/
+DATASET_NAME = "disney-lyrics"
+model_id = "text-embedding-ada-002"
+dataset_path = f"hub://{os.environ['ACTIVELOOP_ORG_ID']}/{DATASET_NAME}"
+print(dataset_path)
+runtime = {"db_engine": True}
+
+with open("lyrics.json", "rb") as f:
+    lyrics = json.load(f)["lyrics"]
+
+# embeddings = [el["embedding"] for el in openai.Embedding.create(input=lyrics, model=model_id)['data']]
+
+# embeddings_np = np.array(embeddings)
+# np.save("embeddings.npy", embeddings_np)
+
+embeddings_np = np.load("embeddings.npy")
+
+print(embeddings_np.shape)
+
+
+# ds = deeplake.empty(dataset_path, runtime=runtime, overwrite=True)
+
+# # https://docs.deeplake.ai/en/latest/Htypes.html
+# with ds:
+#     ds.create_tensor("embedding", htype="embedding", dtype=np.float32, exist_ok=True)
+#     ds.extend({ "embedding": embeddings_np.astype(np.float32)})
+#     ds.summary()
+
+search_term = "Let's get down to business"
+
+embedding = openai.Embedding.create(input=search_term, model="text-embedding-ada-002")[
+    "data"
+][0]["embedding"]
+
+# Format the embedding as a string, so it can be passed in the REST API request.
+embedding_search = ",".join([str(item) for item in embedding])
+
+# embedding_search = ",".join([str(item) for item in embeddings_np[0].tolist()])
+# print(embedding_search)
+
+
+ds = deeplake.load(dataset_path)
+
+# print(embedding_search)
+query = f'select * from (select l2_norm(embedding - ARRAY[{embedding_search}]) as score from "{dataset_path}") order by score desc limit 5'
+with open("foo.txt", "w") as f:
+    f.write(query)
+query_res = ds.query(query)
+print(query_res)

prompts/bot.prompt

@@ -0,0 +1,9 @@
+We have a simple song retrieval system. It accepts a max of 4 emotions. You are tasked to suggest emotions to match the users feelings. Let me show you a couple of examples
+
+Input: "I had a great day!" 
+Output: "Joy and Energy"
+Input: "I am very tired today and I am not feeling weel"
+Output: "Exhaustion, Discomfort, and Fatigue"
+
+If the sentence is too short, you can also suggest just one or two emotions.
+Please, suggest emotions for input = "{content}", reply ONLY with a max of FOUR emotions.

prompts/bot_with_summary.prompt

@@ -0,0 +1,11 @@
+Given the following list of songs:
+
+{songs}
+
+Given an user input. Output the song name, ONLY THE SONG NAME, that will be appropriate with the user feelings/emotions. 
+
+For example: 
+Input: "Today I am not feeling great"
+<SONG_NAME>
+
+The user input is  "{user_input}", reply only with the song name

prompts/summary.prompt

@@ -0,0 +1,7 @@
+This is a disney song, can you output me a string with a one sentence summary of the themes/emotions of the song? Be specific, we will use the emotions/themes as keywords to search later. JUST the summary, not an introduction.
+
+examples
+INPUT: <SONG>
+OUTPUT: <SUMMARY>
+
+{song}

requirements.txt

@@ -0,0 +1,11 @@
+openai
+torch==2.0.1
+torchvision
+python-dotenv
+deeplake
+langchain
+tiktoken
+aiohttp
+cchardet
+aiodns
+streamlit

scrape.py

@@ -0,0 +1,97 @@
+# def get_lyrics_url_from_website():
+#     # https://www.disneyclips.com/lyrics/
+
+import asyncio
+import json
+from collections import defaultdict
+from itertools import chain
+from typing import List, Optional, Tuple, TypedDict
+
+import aiohttp
+from bs4 import BeautifulSoup
+
+URL = "https://www.disneyclips.com/lyrics/"
+
+
+async def get_lyrics_names_and_urls_from_movie_url(
+    movie_name: str, url: str, session: aiohttp.ClientSession
+) -> List[Tuple[str, str]]:
+    async with session.get(url) as response:
+        html = await response.text()
+        soup = BeautifulSoup(html, "html.parser")
+        table = soup.find("table", {"class": "songs"})
+        names_and_urls = []
+        if table:
+            links = table.find_all("a")
+            names_and_urls = []
+            for link in links:
+                names_and_urls.append(
+                    (movie_name, link.text, f"{URL}/{link.get('href')}")
+                )
+        return names_and_urls
+
+
+async def get_lyric_from_lyric_url(
+    movie_name: str, lyric_name: str, url: str, session: aiohttp.ClientSession
+) -> str:
+    async with session.get(url) as response:
+        html = await response.text()
+        soup = BeautifulSoup(html, "html.parser")
+        div = soup.find("div", {"id": "cnt"}).find("div", {"class": "main"})
+        paragraphs = div.find_all("p")
+        text = ""
+        # first <p> has the lyric
+        p = paragraphs[0]
+        for br in p.find_all("br"):
+            br.replace_with(". ")
+        for span in p.find_all("span"):
+            span.decompose()
+        text += p.text
+
+        return (movie_name, lyric_name, text)
+
+
+async def get_movie_names_and_urls(
+    session: aiohttp.ClientSession,
+) -> List[Tuple[str, str]]:
+    async with session.get(URL) as response:
+        html = await response.text()
+        soup = BeautifulSoup(html, "html.parser")
+        links = (
+            soup.find("div", {"id": "cnt"}).find("div", {"class": "main"}).find_all("a")
+        )
+        movie_names_and_urls = [
+            (link.text, f"{URL}/{link.get('href')}") for link in links
+        ]
+        return movie_names_and_urls
+
+
+async def scrape_disney_lyrics():
+    async with aiohttp.ClientSession() as session:
+        data = await get_movie_names_and_urls(session)
+        data = await asyncio.gather(
+            *[
+                asyncio.create_task(
+                    get_lyrics_names_and_urls_from_movie_url(*el, session)
+                )
+                for el in data
+            ]
+        )
+        data = await asyncio.gather(
+            *[
+                asyncio.create_task(get_lyric_from_lyric_url(*data, session))
+                for data in chain(*data)
+            ]
+        )
+
+        result = defaultdict(list)
+
+        for movie_name, lyric_name, lyric_text in data:
+            result[movie_name].append({"name": lyric_name, "text": lyric_text})
+
+        with open("data/lyrics.json", "w") as f:
+            json.dump(result, f)
+
+
+loop = asyncio.get_event_loop()
+loop.run_until_complete(scrape_disney_lyrics())

scripts/create_one_sentence_summary.py

@@ -0,0 +1,36 @@
+from dotenv import load_dotenv
+load_dotenv() 
+
+from langchain.chains import LLMChain
+from langchain.prompts import PromptTemplate
+from pathlib import Path
+from langchain.chat_models import ChatOpenAI
+import json
+from collections import defaultdict
+from pprint import pprint
+
+prompt = PromptTemplate(
+    input_variables=["song"],
+    template=Path("prompts/summary.prompt").read_text(),
+)
+
+llm = ChatOpenAI(temperature=0)
+
+chain = LLMChain(llm=llm, prompt=prompt)
+
+with open("/home/zuppif/Documents/Work/ActiveLoop/ai-shazam/data/lyrics_with_spotify_url.json", "r") as f:
+    data = json.load(f)
+
+lyrics_summaries = {}
+
+for movie, lyrics in data.items():
+    for lyric in lyrics:
+        print(f"Creating summary for {lyric['name']}")
+        summary = chain.run(song=lyric['text'])
+        lyrics_summaries[lyric['name'].lower()] = {"summary": summary,  "embed_url": lyric["embed_url"] }
+    break
+
+with open("/home/zuppif/Documents/Work/ActiveLoop/ai-shazam/data/lyrics_with_spotify_url_and_summary.json", "w") as f:
+    json.dump(lyrics_summaries, f)
+
+pprint(lyrics_summaries)

scripts/keep_only_lyrics_on_spotify.py

@@ -0,0 +1,52 @@
+"""This script will keep only the lyrics that are in the Spotify "Disney Hits" playlist
+"""
+from dotenv import load_dotenv
+
+load_dotenv()
+import json
+
+import spotipy
+from spotipy.oauth2 import SpotifyClientCredentials
+
+name = "Disney hits"
+
+spotify = spotipy.Spotify(auth_manager=SpotifyClientCredentials())
+results = spotify.search(q="playlist:" + name, type="playlist", limit=5)
+items = results["playlists"]["items"]
+
+uri = "spotify:playlist:37i9dQZF1DX8C9xQcOrE6T"
+playlist = spotify.playlist(uri)
+
+# with open("spotify_disney_songs.json", "w") as f:
+#     json.dump(playlist,f)
+
+
+with open("data/lyrics.json", "r") as f:
+    data = json.load(f)
+
+spotify_tracks = {}
+
+for item in playlist["tracks"]["items"]:
+    track = item["track"]
+    track_name = track["name"].lower().split("-")[0].strip()
+    print(track_name)
+    spotify_tracks[track_name] = {
+        "id": track["id"],
+        "embed_url": f"https://open.spotify.com/embed/track/{track['id']}?utm_source=generator",
+    }
+
+# here we add only songs that are in the Disney spotify playlist
+from collections import defaultdict
+
+data_filtered = defaultdict(list)
+tot = 0
+for movie, lyrics in data.items():
+    for lyric in lyrics:
+        name = lyric["name"].lower()
+        if name in spotify_tracks:
+            data_filtered[movie].append({**lyric, **{ 'embed_url' : spotify_tracks[name]['embed_url']}})
+            tot += 1
+print(tot)
+
+with open("data/lyrics_with_spotify_url.json", "w") as f:
+    json.dump(data_filtered, f)

temp.ipynb

@@ -0,0 +1,248 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "26b62e0c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b1a6a020",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/zuppif/miniconda3/envs/activeloop/lib/python3.9/site-packages/deeplake/util/check_latest_version.py:32: UserWarning: A newer version of deeplake (3.4.3) is available. It's recommended that you update to the latest version using `pip install -U deeplake`.\n",
+      "  warnings.warn(\n",
+      "-"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "This dataset can be visualized in Jupyter Notebook by ds.visualize() or at https://app.activeloop.ai/zuppif/disney-lyrics\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "|"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "hub://zuppif/disney-lyrics loaded successfully.\n",
+      "\n",
+      "Deep Lake Dataset in hub://zuppif/disney-lyrics already exists, loading from the storage\n",
+      "Dataset(path='hub://zuppif/disney-lyrics', read_only=True, tensors=['embedding', 'ids', 'metadata', 'text'])\n",
+      "\n",
+      "  tensor     htype     shape      dtype  compression\n",
+      "  -------   -------   -------    -------  ------- \n",
+      " embedding  generic  (85, 1536)  float32   None   \n",
+      "    ids      text     (85, 1)      str     None   \n",
+      " metadata    json     (85, 1)      str     None   \n",
+      "   text      text     (85, 1)      str     None   \n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      " \r",
+      "\r",
+      " \r"
+     ]
+    }
+   ],
+   "source": [
+    "from dotenv import load_dotenv\n",
+    "load_dotenv() \n",
+    "from names import DATASET_ID, MODEL_ID\n",
+    "from data import load_db\n",
+    "import os\n",
+    "from langchain.chains import RetrievalQA, ConversationalRetrievalChain\n",
+    "from langchain.vectorstores import DeepLake\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings(model=MODEL_ID)\n",
+    "dataset_path = f\"hub://{os.environ['ACTIVELOOP_ORG_ID']}/{DATASET_ID}\"\n",
+    "\n",
+    "db = load_db(dataset_path, embedding_function=embeddings, token=os.environ['ACTIVELOOP_TOKEN'], org_id=os.environ[\"ACTIVELOOP_ORG_ID\"], read_only=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 80,
+   "id": "07d8a381",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import LLMChain\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from pathlib import Path\n",
+    "\n",
+    "prompt = PromptTemplate(\n",
+    "    input_variables=[\"content\"],\n",
+    "    template=Path(\"prompts/bot.prompt\").read_text(),\n",
+    ")\n",
+    "\n",
+    "llm = ChatOpenAI(temperature=0.7)\n",
+    "\n",
+    "chain = LLMChain(llm=llm, prompt=prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 81,
+   "id": "ebca722d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Melancholy, Coziness, Nostalgia, Calmness.'"
+      ]
+     },
+     "execution_count": 81,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "emotions = chain.run(content=\"It's rainy\")\n",
+    "emotions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 84,
+   "id": "9598a36c",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'https://open.spotify.com/embed/track/5EeQQ8BVJTRkp1AIKJILGY?utm_source=generator'"
+      ]
+     },
+     "execution_count": 84,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "doc, score = db.similarity_search_with_score(emotions, distance_metric=\"cos\")[0]\n",
+    "doc.metadata[\"embed_url\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 83,
+   "id": "d6214e40",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "        <iframe\n",
+       "            width=\"700\"\n",
+       "            height=\"350\"\n",
+       "            src=\"https://open.spotify.com/embed/track/5EeQQ8BVJTRkp1AIKJILGY?utm_source=generator\"\n",
+       "            frameborder=\"0\"\n",
+       "            allowfullscreen\n",
+       "            \n",
+       "        ></iframe>\n",
+       "        "
+      ],
+      "text/plain": [
+       "<IPython.lib.display.IFrame at 0x7fb0be920a00>"
+      ]
+     },
+     "execution_count": 83,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "doc.metadata[\"embed_url\"]\n",
+    "\n",
+    "from IPython.display import IFrame\n",
+    "IFrame(doc.metadata[\"embed_url\"], width=700, height=350)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "28ae2c63",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Dataset(path='hub://zuppif/disney-lyrics', read_only=True, index=Index([()]), tensors=['embedding', 'ids', 'metadata', 'text'])"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "db.ds.query(\"select * where contains(\\\"text\\\", 'Did they') limit 2\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1780552c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}