upgrade deeplake version and twitter notebook

docs/use_cases/code/twitter-the-algorithm-analysis-deeplake.ipynb

@@ -120,7 +120,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "db = DeepLake.from_documents(texts, embeddings, dataset_path=\"hub://davitbun/twitter-algorithm\")"
+    "username = \"davitbun\" # replace with your username from app.activeloop.ai\n",
+    "db = DeepLake(dataset_path=f\"hub://{username}/twitter-algorithm-4\", embedding_function=embeddings, public=True) #dataset owuld be public\n",
+    "db.add_documents(texts)"
    ]
   },
   {
@@ -133,61 +135,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "-"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "This dataset can be visualized in Jupyter Notebook by ds.visualize() or at https://app.activeloop.ai/davitbun/twitter-algorithm\n",
-      "\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "-"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "hub://davitbun/twitter-algorithm loaded successfully.\n",
-      "\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Deep Lake Dataset in hub://davitbun/twitter-algorithm already exists, loading from the storage\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Dataset(path='hub://davitbun/twitter-algorithm', read_only=True, tensors=['embedding', 'ids', 'metadata', 'text'])\n",
-      "\n",
-      "  tensor     htype       shape       dtype  compression\n",
-      "  -------   -------     -------     -------  ------- \n",
-      " embedding  generic  (23152, 1536)  float32   None   \n",
-      "    ids      text     (23152, 1)      str     None   \n",
-      " metadata    json     (23152, 1)      str     None   \n",
-      "   text      text     (23152, 1)      str     None   \n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "db = DeepLake(dataset_path=\"hub://davitbun/twitter-algorithm\", read_only=True, embedding_function=embeddings)"
    ]
@@ -203,7 +153,7 @@
     "retriever.search_kwargs['distance_metric'] = 'cos'\n",
     "retriever.search_kwargs['fetch_k'] = 100\n",
     "retriever.search_kwargs['maximal_marginal_relevance'] = True\n",
-    "retriever.search_kwargs['k'] = 20"
+    "retriever.search_kwargs['k'] = 10"
    ]
   },
   {
@@ -241,7 +191,7 @@
     "from langchain.chat_models import ChatOpenAI\n",
     "from langchain.chains import ConversationalRetrievalChain\n",
     "\n",
-    "model = ChatOpenAI(model='gpt-4') # 'gpt-3.5-turbo',\n",
+    "model = ChatOpenAI(model='gpt-3.5-turbo') # switch to 'gpt-4'\n",
     "qa = ConversationalRetrievalChain.from_llm(model,retriever=retriever)"
    ]
   },

pyproject.toml

@@ -56,7 +56,7 @@ arxiv = {version = "^1.4", optional = true}
 pypdf = {version = "^3.4.0", optional = true}
 networkx = {version="^2.6.3", optional = true}
 aleph-alpha-client = {version="^2.15.0", optional = true}
-deeplake = {version = "^3.2.21", optional = true}
+deeplake = {version = "^3.3.0", optional = true}
 pgvector = {version = "^0.1.6", optional = true}
 psycopg2-binary = {version = "^2.9.5", optional = true}
 #boto3 = {version = "^1.26.96", optional = true} # TODO: fix it, commented because the version failed with deeplake