nb/QA_chains.ipynb: cleaned the clutter

notebooks/QA_chains.ipynb

@@ -47,19 +47,7 @@
     "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
     "# from langchain_huggingface import HuggingFaceEmbeddings\n",
     "\n",
-    "# from langchain_core.embeddings import Embeddings\n",
-    "# from chromadb.api.types import EmbeddingFunction, Documents\n",
-    "# class LangChainEmbeddingAdapter(EmbeddingFunction[Documents]):\n",
-    "#     def __init__(self, ef: Embeddings):\n",
-    "#         self.ef = ef\n",
-    "\n",
-    "#     def __call__(self, input: Documents) -> Embeddings:\n",
-    "#         # LC EFs also have embed_query but Chroma doesn't support that so we just use embed_documents\n",
-    "#         # TODO: better type checking\n",
-    "#         return self.ef.embed_documents(input)\n",
-    "\n",
-    "lc_embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
-    "# chroma_ef = LangChainEmbeddingAdapter(lc_embeddings)"
+    "lc_embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")"
    ]
   },
   {
@@ -79,12 +67,6 @@
     "client = chromadb.PersistentClient(\n",
     "    path=persist_directory\n",
     "    )\n",
-    "# print(f'Database has {client.count_collections()} collections')\n",
-    "# collection = client.get_or_create_collection(\n",
-    "#     name=collection_name,\n",
-    "#     embedding_function = chroma_ef,\n",
-    "#     )\n",
-    "# print(f'Collection {collection_name} has {collection.count()} entries')\n",
     "\n",
     "from langchain_community.vectorstores import Chroma\n",
     "\n",