app with emotions

app.py

@@ -13,36 +13,33 @@ from langchain.embeddings.openai import OpenAIEmbeddings
 
 from data import load_db
 from names import DATASET_ID, MODEL_ID
-import json 
+
 
 @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,
-    # )
-
-    with open("/home/zuppif/Documents/Work/ActiveLoop/ai-shazam/data/lyrics_with_spotify_url_and_summary.json", "r") as f:
-        songs = json.load(f)
+    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=["songs", "user_input"],
-        template=Path("prompts/bot_with_summary.prompt").read_text(),
+        input_variables=["content"],
+        template=Path("prompts/bot.prompt").read_text(),
     )
 
     llm = ChatOpenAI(temperature=0.7)
 
     chain = LLMChain(llm=llm, prompt=prompt)
 
-    return chain, songs, json.dumps(songs)
+    return db, chain
 
-chain, songs, songs_json = init()
+db, chain = init()
 
 st.title("Disney song for you")
 
@@ -56,18 +53,16 @@ placeholder_emotions = st.empty()
 placeholder = st.empty()
 
 def get_emotions(user_input):
-    song_name = chain.run(songs=songs_json, user_input=user_input)
-    song_name.replace('\'', '')
-    print(f"Song: {song_name}")
-    song = songs[song_name.lower()]
-    # matches = db.similarity_search_with_score(emotions, distance_metric="cos")
-    # print(matches)
-    # doc, score = matches[0]
+    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_emotions:
+        st.write(emotions)
     with placeholder:
-        embed_url = song["embed_url"]
+        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>")
 

data.py

@@ -45,4 +45,4 @@ def load_db(dataset_path: str, *args, **kwargs) -> DeepLake:
 
 if __name__ == "__main__":
     dataset_path = f"hub://{os.environ['ACTIVELOOP_ORG_ID']}/{DATASET_ID}"
-    create_db(dataset_path, "data/lyrics_with_spotify_url.json")
+    create_db(dataset_path, "data/emotions_with_spotify_url.json")

data/lyrics_with_spotify_url.json

@@ -492,4 +492,4 @@
       "embed_url": "https://open.spotify.com/embed/track/0d83zVs3OmdjrhfoAxg1dE?utm_source=generator"
     }
   ]
-}
+}

names.py

@@ -1,2 +1,4 @@
 MODEL_ID = "text-embedding-ada-002"
-DATASET_ID = "disney-lyrics"
+# DATASET_ID = "disney-lyrics"
+DATASET_ID = "disney-lyrics-emotions"
+

prompts/bot.prompt

@@ -6,4 +6,4 @@ 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.
+Please, suggest emotions for input = "{content}", reply ONLY with a max of 4 emotions.

prompts/bot_with_summary.prompt

@@ -4,7 +4,7 @@ You the following list of songs:
 
 {songs}
 
-Given a input, output the song name that matches its content. Just the song name
+Given a input, output the song name that its content vibe, emotions, theme. Just the song name. If the content containes negative sentiment, please provide a song name to help the user instead.
 
 For example: 
 Input: "Today I am not feeling great"

scripts/create_one_sentence_summary.py

@@ -1,14 +1,16 @@
 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
+load_dotenv()
+
 import json
 from collections import defaultdict
+from pathlib import Path
 from pprint import pprint
 
+from langchain.chains import LLMChain
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts import PromptTemplate
+
 prompt = PromptTemplate(
     input_variables=["song"],
     template=Path("prompts/summary.prompt").read_text(),
@@ -18,7 +20,10 @@ 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:
+with open(
+    "/home/zuppif/Documents/Work/ActiveLoop/ai-shazam/data/lyrics_with_spotify_url.json",
+    "r",
+) as f:
     data = json.load(f)
 
 lyrics_summaries = {}
@@ -26,10 +31,16 @@ 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"] }
-
-with open("/home/zuppif/Documents/Work/ActiveLoop/ai-shazam/data/lyrics_with_spotify_url_and_summary.json", "w") as f:
+        summary = chain.run(song=lyric["text"])
+        lyrics_summaries[lyric["name"].lower()] = {
+            "summary": summary,
+            "embed_url": lyric["embed_url"],
+        }
+
+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)
+pprint(lyrics_summaries)

scripts/keep_only_lyrics_on_spotify.py

@@ -44,7 +44,9 @@ 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']}})
+            data_filtered[movie].append(
+                {**lyric, **{"embed_url": spotify_tracks[name]["embed_url"]}}
+            )
             tot += 1
 print(tot)
 

temp.ipynb

@@ -13,7 +13,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 74,
    "id": "b1a6a020",
    "metadata": {
     "scrolled": true
@@ -23,16 +23,14 @@
      "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",
+      "This dataset can be visualized in Jupyter Notebook by ds.visualize() or at https://app.activeloop.ai/zuppif/disney-lyrics-emotions\n",
       "\n"
      ]
     },
@@ -40,17 +38,17 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "|"
+      "-"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "hub://zuppif/disney-lyrics loaded successfully.\n",
+      "hub://zuppif/disney-lyrics-emotions 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",
+      "Deep Lake Dataset in hub://zuppif/disney-lyrics-emotions already exists, loading from the storage\n",
+      "Dataset(path='hub://zuppif/disney-lyrics-emotions', read_only=True, tensors=['embedding', 'ids', 'metadata', 'text'])\n",
       "\n",
       "  tensor     htype     shape      dtype  compression\n",
       "  -------   -------   -------    -------  ------- \n",
@@ -91,7 +89,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 80,
+   "execution_count": 75,
    "id": "07d8a381",
    "metadata": {},
    "outputs": [],
@@ -112,56 +110,43 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
+   "execution_count": 76,
    "id": "ebca722d",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'Melancholy, Coziness, Nostalgia, Calmness.'"
+       "'Exhaustion, Fatigue, Sleepiness, Drained.'"
       ]
      },
-     "execution_count": 81,
+     "execution_count": 76,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "emotions = chain.run(content=\"It's rainy\")\n",
+    "emotions = chain.run(content=\"Damn I am feeling so tired\")\n",
     "emotions"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 84,
+   "execution_count": 77,
    "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": [
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[(Document(page_content='Hopeful, determined, inspired, optimistic, longing, driven, passionate, adventurous.', metadata={'movie': 'Hercules', 'name': 'Go the Distance', 'embed_url': 'https://open.spotify.com/embed/track/0D1OY0M5A0qD5HGBvFmFid?utm_source=generator'}), 0.8135085701942444), (Document(page_content='upset, mad, regret, sad, fine, longing, hopeful, impatient', metadata={'movie': 'Encanto', 'name': 'Waiting on a Miracle', 'embed_url': 'https://open.spotify.com/embed/track/3oRW9ZGPRbLRMneQ5lwflt?utm_source=generator'}), 0.8108540177345276), (Document(page_content='nasty, repentant, magic, sad, lonely, bored, withdrawn, busy', metadata={'movie': 'The Little Mermaid', 'name': 'Poor Unfortunate Souls', 'embed_url': 'https://open.spotify.com/embed/track/7zsw78LtXUD7JfEwH64HK2?utm_source=generator'}), 0.8080281615257263), (Document(page_content='hopeful, optimistic, dreamy, inspired, happy, content, fulfilled, grateful', metadata={'movie': 'Pinocchio', 'name': 'When You Wish Upon a Star', 'embed_url': 'https://open.spotify.com/embed/track/1WrPa4lrIddctGWAIYYfP9?utm_source=generator'}), 0.8055723309516907)]\n",
+      "https://open.spotify.com/embed/track/0D1OY0M5A0qD5HGBvFmFid?utm_source=generator\n",
+      "page_content='Hopeful, determined, inspired, optimistic, longing, driven, passionate, adventurous.' metadata={'movie': 'Hercules', 'name': 'Go the Distance', 'embed_url': 'https://open.spotify.com/embed/track/0D1OY0M5A0qD5HGBvFmFid?utm_source=generator'}\n"
+     ]
+    },
     {
      "data": {
       "text/html": [
@@ -169,7 +154,7 @@
        "        <iframe\n",
        "            width=\"700\"\n",
        "            height=\"350\"\n",
-       "            src=\"https://open.spotify.com/embed/track/5EeQQ8BVJTRkp1AIKJILGY?utm_source=generator\"\n",
+       "            src=\"https://open.spotify.com/embed/track/0D1OY0M5A0qD5HGBvFmFid?utm_source=generator\"\n",
        "            frameborder=\"0\"\n",
        "            allowfullscreen\n",
        "            \n",
@@ -177,48 +162,112 @@
        "        "
       ],
       "text/plain": [
-       "<IPython.lib.display.IFrame at 0x7fb0be920a00>"
+       "<IPython.lib.display.IFrame at 0x7f1890ed7430>"
       ]
      },
-     "execution_count": 83,
+     "execution_count": 77,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "doc.metadata[\"embed_url\"]\n",
+    "matches = db.similarity_search_with_score(emotions, distance_metric=\"cos\")\n",
+    "print(matches)\n",
+    "doc, score = matches[0]\n",
+    "print(doc.metadata[\"embed_url\"])\n",
+    "print(doc)\n",
     "\n",
     "from IPython.display import IFrame\n",
     "IFrame(doc.metadata[\"embed_url\"], width=700, height=350)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "e59a45b7",
+   "metadata": {},
+   "source": [
+    "## Using all the songs emotions in the prommpt"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "id": "28ae2c63",
+   "execution_count": 66,
+   "id": "7b10a5f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "prompt = PromptTemplate(\n",
+    "    input_variables=[\"songs\", \"user_input\"],\n",
+    "    template=Path(\"prompts/bot_with_summary.prompt\").read_text(),\n",
+    ")\n",
+    "\n",
+    "llm = ChatOpenAI(temperature=0.7)\n",
+    "\n",
+    "chain = LLMChain(llm=llm, prompt=prompt)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "70b8c445",
+   "metadata": {},
+   "source": [
+    "Let's create the songs string"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "id": "36df1c27",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"data/emotions_with_spotify_url.json\", \"r\") as f:\n",
+    "    data = json.load(f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "id": "e3e496da",
    "metadata": {
     "scrolled": true
    },
+   "outputs": [],
+   "source": [
+    "songs_str = \"\"\n",
+    "\n",
+    "for movie, songs in data.items():\n",
+    "    for song in songs:\n",
+    "        songs_str += f\"{song['name']}: {song['text']}\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "id": "070b09d8",
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Dataset(path='hub://zuppif/disney-lyrics', read_only=True, index=Index([()]), tensors=['embedding', 'ids', 'metadata', 'text'])"
+       "'Zero to Hero'"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 71,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "db.ds.query(\"select * where contains(\\\"text\\\", 'Did they') limit 2\")"
+    "chain.run(songs=songs_str, user_input=\"Damn I am feeling so tired\")"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1780552c",
+   "id": "b6c6e90c",
    "metadata": {},
    "outputs": [],
    "source": []