Changed HF HOME advanced contextual rag

app_inference.py

@@ -11,7 +11,7 @@ SYSTEM_MESSAGE = "You are a hepful, knowledgeable assistant"
 
 # ENV VARS
 # To avert Permision error with transformer and hf models
-# os.environ['SENTENCE_TRANSFORMERS_HOME'] = '.'
+os.environ['SENTENCE_TRANSFORMERS_HOME'] = '.'
 token = os.getenv("HF_TOKEN_WRITE") # Must be a write token
 # STREAMLIT UI AREA
 
@@ -21,7 +21,10 @@ submit = st.button("Submit")
 
 # MODEL AREA
 # Use the token to authenticate
-login(token=token, write_permission=True)
+login(token=token, 
+      write_permission=True     # Must be set to True when we pass in our own token
+                                # Otherwise we get Permission Denied.
+      )
 model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
 
 @st.cache_resource

examples/techniques/Contextual_RAG.ipynb

@@ -41,7 +41,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -54,20 +54,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/jovian/Projects/LocalRAG/.venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "from langchain_google_genai import ChatGoogleGenerativeAI"
+    "from langchain.chains.summarize import load_summarize_chain"
    ]
   },
   {
@@ -76,118 +67,68 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chains.summarize import load_summarize_chain"
+    "# from langchain_google_genai import ChatGoogleGenerativeAI\n",
+    "# import os\n",
+    "# from dotenv import load_dotenv\n",
+    "\n",
+    "# if not load_dotenv():\n",
+    "#     print(\"API keys may not have been loaded succesfully\")\n",
+    "# google_api_key = os.getenv(\"GOOGLE_API_KEY\")\n",
+    "\n",
+    "# llm = ChatGoogleGenerativeAI(model=\"gemini-pro\", api_key=google_api_key)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
-    "from dotenv import load_dotenv\n",
+    "from langchain_ollama.llms import OllamaLLM\n",
     "\n",
-    "if not load_dotenv():\n",
-    "    print(\"API keys may not have been loaded succesfully\")\n",
-    "google_api_key = os.getenv(\"GOOGLE_API_KEY\")"
+    "# A lightweigh model for local inference\n",
+    "llm = OllamaLLM(model=\"llama3.2:1b-instruct-q4_K_M\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm = ChatGoogleGenerativeAI(model=\"gemini-pro\", api_key=google_api_key)"
+    "loader = PyMuPDFLoader(\"data/State Machines.pdf\")\n",
+    "docs = loader.load()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
-    "loader = PyMuPDFLoader(\"data/State Machines.pdf\")\n",
-    "docs = loader.load()"
+    "text_splitter = CharacterTextSplitter.from_tiktoken_encoder(chunk_size=8000, chunk_overlap=0)\n",
+    "split_docs = text_splitter.split_documents(docs)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "text_splitter = CharacterTextSplitter.from_tiktoken_encoder(chunk_size=1000, chunk_overlap=0)\n",
-    "split_docs = text_splitter.split_documents(docs)"
+    "output_key = \"output_text\""
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 22,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/tmp/ipykernel_13575/4103169951.py:32: LangChainDeprecationWarning: The method `Chain.__call__` was deprecated in langchain 0.1.0 and will be removed in 1.0. Use :meth:`~invoke` instead.\n",
-      "  result = chain({\"input_documents\": split_docs}, return_only_outputs=True)\n",
-      "Retrying langchain_google_genai.chat_models._chat_with_retry.<locals>._chat_with_retry in 2.0 seconds as it raised ResourceExhausted: 429 Resource has been exhausted (e.g. check quota)..\n"
-     ]
-    },
-    {
-     "ename": "ResourceExhausted",
-     "evalue": "429 Resource has been exhausted (e.g. check quota).",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mResourceExhausted\u001b[0m                         Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[11], line 32\u001b[0m\n\u001b[1;32m     22\u001b[0m \u001b[38;5;66;03m# Load refine chain\u001b[39;00m\n\u001b[1;32m     23\u001b[0m chain \u001b[38;5;241m=\u001b[39m load_summarize_chain(\n\u001b[1;32m     24\u001b[0m     llm\u001b[38;5;241m=\u001b[39mllm,\n\u001b[1;32m     25\u001b[0m     chain_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrefine\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     30\u001b[0m     output_key\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124moutput_text\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m     31\u001b[0m )\n\u001b[0;32m---> 32\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[43mchain\u001b[49m\u001b[43m(\u001b[49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43minput_documents\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43msplit_docs\u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain_core/_api/deprecation.py:179\u001b[0m, in \u001b[0;36mdeprecated.<locals>.deprecate.<locals>.warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    177\u001b[0m     warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    178\u001b[0m     emit_warning()\n\u001b[0;32m--> 179\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain/chains/base.py:389\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)\u001b[0m\n\u001b[1;32m    357\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Execute the chain.\u001b[39;00m\n\u001b[1;32m    358\u001b[0m \n\u001b[1;32m    359\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    380\u001b[0m \u001b[38;5;124;03m        `Chain.output_keys`.\u001b[39;00m\n\u001b[1;32m    381\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    382\u001b[0m config \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m    383\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks,\n\u001b[1;32m    384\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtags\u001b[39m\u001b[38;5;124m\"\u001b[39m: tags,\n\u001b[1;32m    385\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmetadata\u001b[39m\u001b[38;5;124m\"\u001b[39m: metadata,\n\u001b[1;32m    386\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_name\u001b[39m\u001b[38;5;124m\"\u001b[39m: run_name,\n\u001b[1;32m    387\u001b[0m }\n\u001b[0;32m--> 389\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    390\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    391\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast\u001b[49m\u001b[43m(\u001b[49m\u001b[43mRunnableConfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[43mk\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitems\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    392\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    393\u001b[0m \u001b[43m    \u001b[49m\u001b[43minclude_run_info\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude_run_info\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    394\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain/chains/base.py:170\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    169\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 170\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    171\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m    173\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m include_run_info:\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain/chains/base.py:160\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    157\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    158\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_inputs(inputs)\n\u001b[1;32m    159\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 160\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    161\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    162\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m    163\u001b[0m     )\n\u001b[1;32m    165\u001b[0m     final_outputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(\n\u001b[1;32m    166\u001b[0m         inputs, outputs, return_only_outputs\n\u001b[1;32m    167\u001b[0m     )\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain/chains/combine_documents/base.py:138\u001b[0m, in \u001b[0;36mBaseCombineDocumentsChain._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m    136\u001b[0m \u001b[38;5;66;03m# Other keys are assumed to be needed for LLM prediction\u001b[39;00m\n\u001b[1;32m    137\u001b[0m other_keys \u001b[38;5;241m=\u001b[39m {k: v \u001b[38;5;28;01mfor\u001b[39;00m k, v \u001b[38;5;129;01min\u001b[39;00m inputs\u001b[38;5;241m.\u001b[39mitems() \u001b[38;5;28;01mif\u001b[39;00m k \u001b[38;5;241m!=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minput_key}\n\u001b[0;32m--> 138\u001b[0m output, extra_return_dict \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcombine_docs\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    139\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdocs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m_run_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mother_keys\u001b[49m\n\u001b[1;32m    140\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    141\u001b[0m extra_return_dict[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_key] \u001b[38;5;241m=\u001b[39m output\n\u001b[1;32m    142\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m extra_return_dict\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain/chains/combine_documents/refine.py:160\u001b[0m, in \u001b[0;36mRefineDocumentsChain.combine_docs\u001b[0;34m(self, docs, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    158\u001b[0m     base_inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_construct_refine_inputs(doc, res)\n\u001b[1;32m    159\u001b[0m     inputs \u001b[38;5;241m=\u001b[39m {\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mbase_inputs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs}\n\u001b[0;32m--> 160\u001b[0m     res \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrefine_llm_chain\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpredict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    161\u001b[0m     refine_steps\u001b[38;5;241m.\u001b[39mappend(res)\n\u001b[1;32m    162\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_construct_result(refine_steps, res)\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain/chains/llm.py:316\u001b[0m, in \u001b[0;36mLLMChain.predict\u001b[0;34m(self, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    301\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpredict\u001b[39m(\u001b[38;5;28mself\u001b[39m, callbacks: Callbacks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28mstr\u001b[39m:\n\u001b[1;32m    302\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Format prompt with kwargs and pass to LLM.\u001b[39;00m\n\u001b[1;32m    303\u001b[0m \n\u001b[1;32m    304\u001b[0m \u001b[38;5;124;03m    Args:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    314\u001b[0m \u001b[38;5;124;03m            completion = llm.predict(adjective=\"funny\")\u001b[39;00m\n\u001b[1;32m    315\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 316\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_key]\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain_core/_api/deprecation.py:179\u001b[0m, in \u001b[0;36mdeprecated.<locals>.deprecate.<locals>.warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    177\u001b[0m     warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    178\u001b[0m     emit_warning()\n\u001b[0;32m--> 179\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain/chains/base.py:389\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)\u001b[0m\n\u001b[1;32m    357\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Execute the chain.\u001b[39;00m\n\u001b[1;32m    358\u001b[0m \n\u001b[1;32m    359\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    380\u001b[0m \u001b[38;5;124;03m        `Chain.output_keys`.\u001b[39;00m\n\u001b[1;32m    381\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    382\u001b[0m config \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m    383\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks,\n\u001b[1;32m    384\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtags\u001b[39m\u001b[38;5;124m\"\u001b[39m: tags,\n\u001b[1;32m    385\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmetadata\u001b[39m\u001b[38;5;124m\"\u001b[39m: metadata,\n\u001b[1;32m    386\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_name\u001b[39m\u001b[38;5;124m\"\u001b[39m: run_name,\n\u001b[1;32m    387\u001b[0m }\n\u001b[0;32m--> 389\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    390\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    391\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast\u001b[49m\u001b[43m(\u001b[49m\u001b[43mRunnableConfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[43mk\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitems\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    392\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    393\u001b[0m \u001b[43m    \u001b[49m\u001b[43minclude_run_info\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude_run_info\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    394\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain/chains/base.py:170\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    169\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 170\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    171\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m    173\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m include_run_info:\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain/chains/base.py:160\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    157\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    158\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_inputs(inputs)\n\u001b[1;32m    159\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 160\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    161\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    162\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m    163\u001b[0m     )\n\u001b[1;32m    165\u001b[0m     final_outputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(\n\u001b[1;32m    166\u001b[0m         inputs, outputs, return_only_outputs\n\u001b[1;32m    167\u001b[0m     )\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain/chains/llm.py:126\u001b[0m, in \u001b[0;36mLLMChain._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m    121\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_call\u001b[39m(\n\u001b[1;32m    122\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    123\u001b[0m     inputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any],\n\u001b[1;32m    124\u001b[0m     run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    125\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Dict[\u001b[38;5;28mstr\u001b[39m, \u001b[38;5;28mstr\u001b[39m]:\n\u001b[0;32m--> 126\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[43m[\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    127\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcreate_outputs(response)[\u001b[38;5;241m0\u001b[39m]\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain/chains/llm.py:138\u001b[0m, in \u001b[0;36mLLMChain.generate\u001b[0;34m(self, input_list, run_manager)\u001b[0m\n\u001b[1;32m    136\u001b[0m callbacks \u001b[38;5;241m=\u001b[39m run_manager\u001b[38;5;241m.\u001b[39mget_child() \u001b[38;5;28;01mif\u001b[39;00m run_manager \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    137\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm, BaseLanguageModel):\n\u001b[0;32m--> 138\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate_prompt\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    139\u001b[0m \u001b[43m        \u001b[49m\u001b[43mprompts\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    140\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    141\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    142\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    143\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    144\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    145\u001b[0m     results \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm\u001b[38;5;241m.\u001b[39mbind(stop\u001b[38;5;241m=\u001b[39mstop, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm_kwargs)\u001b[38;5;241m.\u001b[39mbatch(\n\u001b[1;32m    146\u001b[0m         cast(List, prompts), {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks}\n\u001b[1;32m    147\u001b[0m     )\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:784\u001b[0m, in \u001b[0;36mBaseChatModel.generate_prompt\u001b[0;34m(self, prompts, stop, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    776\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mgenerate_prompt\u001b[39m(\n\u001b[1;32m    777\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    778\u001b[0m     prompts: \u001b[38;5;28mlist\u001b[39m[PromptValue],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    781\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m    782\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m LLMResult:\n\u001b[1;32m    783\u001b[0m     prompt_messages \u001b[38;5;241m=\u001b[39m [p\u001b[38;5;241m.\u001b[39mto_messages() \u001b[38;5;28;01mfor\u001b[39;00m p \u001b[38;5;129;01min\u001b[39;00m prompts]\n\u001b[0;32m--> 784\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprompt_messages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:641\u001b[0m, in \u001b[0;36mBaseChatModel.generate\u001b[0;34m(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m    639\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m run_managers:\n\u001b[1;32m    640\u001b[0m             run_managers[i]\u001b[38;5;241m.\u001b[39mon_llm_error(e, response\u001b[38;5;241m=\u001b[39mLLMResult(generations\u001b[38;5;241m=\u001b[39m[]))\n\u001b[0;32m--> 641\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    642\u001b[0m flattened_outputs \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m    643\u001b[0m     LLMResult(generations\u001b[38;5;241m=\u001b[39m[res\u001b[38;5;241m.\u001b[39mgenerations], llm_output\u001b[38;5;241m=\u001b[39mres\u001b[38;5;241m.\u001b[39mllm_output)  \u001b[38;5;66;03m# type: ignore[list-item]\u001b[39;00m\n\u001b[1;32m    644\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m res \u001b[38;5;129;01min\u001b[39;00m results\n\u001b[1;32m    645\u001b[0m ]\n\u001b[1;32m    646\u001b[0m llm_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_combine_llm_outputs([res\u001b[38;5;241m.\u001b[39mllm_output \u001b[38;5;28;01mfor\u001b[39;00m res \u001b[38;5;129;01min\u001b[39;00m results])\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:631\u001b[0m, in \u001b[0;36mBaseChatModel.generate\u001b[0;34m(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m    628\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i, m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(messages):\n\u001b[1;32m    629\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    630\u001b[0m         results\u001b[38;5;241m.\u001b[39mappend(\n\u001b[0;32m--> 631\u001b[0m             \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_generate_with_cache\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    632\u001b[0m \u001b[43m                \u001b[49m\u001b[43mm\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    633\u001b[0m \u001b[43m                \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    634\u001b[0m \u001b[43m                \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_managers\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_managers\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    635\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    636\u001b[0m \u001b[43m            \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    637\u001b[0m         )\n\u001b[1;32m    638\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    639\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m run_managers:\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:853\u001b[0m, in \u001b[0;36mBaseChatModel._generate_with_cache\u001b[0;34m(self, messages, stop, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m    851\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    852\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m inspect\u001b[38;5;241m.\u001b[39msignature(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_generate)\u001b[38;5;241m.\u001b[39mparameters\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_manager\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[0;32m--> 853\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_generate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    854\u001b[0m \u001b[43m            \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m    855\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    856\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    857\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_generate(messages, stop\u001b[38;5;241m=\u001b[39mstop, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain_google_genai/chat_models.py:980\u001b[0m, in \u001b[0;36mChatGoogleGenerativeAI._generate\u001b[0;34m(self, messages, stop, run_manager, tools, functions, safety_settings, tool_config, generation_config, **kwargs)\u001b[0m\n\u001b[1;32m    958\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_generate\u001b[39m(\n\u001b[1;32m    959\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    960\u001b[0m     messages: List[BaseMessage],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    969\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m    970\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ChatResult:\n\u001b[1;32m    971\u001b[0m     request \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_prepare_request(\n\u001b[1;32m    972\u001b[0m         messages,\n\u001b[1;32m    973\u001b[0m         stop\u001b[38;5;241m=\u001b[39mstop,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    978\u001b[0m         generation_config\u001b[38;5;241m=\u001b[39mgeneration_config,\n\u001b[1;32m    979\u001b[0m     )\n\u001b[0;32m--> 980\u001b[0m     response: GenerateContentResponse \u001b[38;5;241m=\u001b[39m \u001b[43m_chat_with_retry\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    981\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrequest\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    982\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    983\u001b[0m \u001b[43m        \u001b[49m\u001b[43mgeneration_method\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate_content\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    984\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdefault_metadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    985\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    986\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m _response_to_result(response)\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain_google_genai/chat_models.py:205\u001b[0m, in \u001b[0;36m_chat_with_retry\u001b[0;34m(generation_method, **kwargs)\u001b[0m\n\u001b[1;32m    202\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    203\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[0;32m--> 205\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_chat_with_retry\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/tenacity/__init__.py:336\u001b[0m, in \u001b[0;36mBaseRetrying.wraps.<locals>.wrapped_f\u001b[0;34m(*args, **kw)\u001b[0m\n\u001b[1;32m    334\u001b[0m copy \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcopy()\n\u001b[1;32m    335\u001b[0m wrapped_f\u001b[38;5;241m.\u001b[39mstatistics \u001b[38;5;241m=\u001b[39m copy\u001b[38;5;241m.\u001b[39mstatistics  \u001b[38;5;66;03m# type: ignore[attr-defined]\u001b[39;00m\n\u001b[0;32m--> 336\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mcopy\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkw\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/tenacity/__init__.py:475\u001b[0m, in \u001b[0;36mRetrying.__call__\u001b[0;34m(self, fn, *args, **kwargs)\u001b[0m\n\u001b[1;32m    473\u001b[0m retry_state \u001b[38;5;241m=\u001b[39m RetryCallState(retry_object\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m, fn\u001b[38;5;241m=\u001b[39mfn, args\u001b[38;5;241m=\u001b[39margs, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[1;32m    474\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m--> 475\u001b[0m     do \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43miter\u001b[49m\u001b[43m(\u001b[49m\u001b[43mretry_state\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretry_state\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    476\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(do, DoAttempt):\n\u001b[1;32m    477\u001b[0m         \u001b[38;5;28;01mtry\u001b[39;00m:\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/tenacity/__init__.py:376\u001b[0m, in \u001b[0;36mBaseRetrying.iter\u001b[0;34m(self, retry_state)\u001b[0m\n\u001b[1;32m    374\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    375\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m action \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39miter_state\u001b[38;5;241m.\u001b[39mactions:\n\u001b[0;32m--> 376\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[43maction\u001b[49m\u001b[43m(\u001b[49m\u001b[43mretry_state\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    377\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m result\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/tenacity/__init__.py:418\u001b[0m, in \u001b[0;36mBaseRetrying._post_stop_check_actions.<locals>.exc_check\u001b[0;34m(rs)\u001b[0m\n\u001b[1;32m    416\u001b[0m retry_exc \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mretry_error_cls(fut)\n\u001b[1;32m    417\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mreraise:\n\u001b[0;32m--> 418\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[43mretry_exc\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreraise\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    419\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m retry_exc \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfut\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mexception\u001b[39;00m()\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/tenacity/__init__.py:185\u001b[0m, in \u001b[0;36mRetryError.reraise\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    183\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mreraise\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m t\u001b[38;5;241m.\u001b[39mNoReturn:\n\u001b[1;32m    184\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlast_attempt\u001b[38;5;241m.\u001b[39mfailed:\n\u001b[0;32m--> 185\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlast_attempt\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresult\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    186\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\n",
-      "File \u001b[0;32m/usr/lib/python3.10/concurrent/futures/_base.py:451\u001b[0m, in \u001b[0;36mFuture.result\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    449\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m CancelledError()\n\u001b[1;32m    450\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_state \u001b[38;5;241m==\u001b[39m FINISHED:\n\u001b[0;32m--> 451\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__get_result\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    453\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_condition\u001b[38;5;241m.\u001b[39mwait(timeout)\n\u001b[1;32m    455\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_state \u001b[38;5;129;01min\u001b[39;00m [CANCELLED, CANCELLED_AND_NOTIFIED]:\n",
-      "File \u001b[0;32m/usr/lib/python3.10/concurrent/futures/_base.py:403\u001b[0m, in \u001b[0;36mFuture.__get_result\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    401\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_exception:\n\u001b[1;32m    402\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 403\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_exception\n\u001b[1;32m    404\u001b[0m     \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[1;32m    405\u001b[0m         \u001b[38;5;66;03m# Break a reference cycle with the exception in self._exception\u001b[39;00m\n\u001b[1;32m    406\u001b[0m         \u001b[38;5;28mself\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/tenacity/__init__.py:478\u001b[0m, in \u001b[0;36mRetrying.__call__\u001b[0;34m(self, fn, *args, **kwargs)\u001b[0m\n\u001b[1;32m    476\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(do, DoAttempt):\n\u001b[1;32m    477\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 478\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    479\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m:  \u001b[38;5;66;03m# noqa: B902\u001b[39;00m\n\u001b[1;32m    480\u001b[0m         retry_state\u001b[38;5;241m.\u001b[39mset_exception(sys\u001b[38;5;241m.\u001b[39mexc_info())  \u001b[38;5;66;03m# type: ignore[arg-type]\u001b[39;00m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain_google_genai/chat_models.py:203\u001b[0m, in \u001b[0;36m_chat_with_retry.<locals>._chat_with_retry\u001b[0;34m(**kwargs)\u001b[0m\n\u001b[1;32m    199\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m ChatGoogleGenerativeAIError(\n\u001b[1;32m    200\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mInvalid argument provided to Gemini: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    201\u001b[0m     ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m    202\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m--> 203\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/langchain_google_genai/chat_models.py:187\u001b[0m, in \u001b[0;36m_chat_with_retry.<locals>._chat_with_retry\u001b[0;34m(**kwargs)\u001b[0m\n\u001b[1;32m    184\u001b[0m \u001b[38;5;129m@retry_decorator\u001b[39m\n\u001b[1;32m    185\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_chat_with_retry\u001b[39m(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Any:\n\u001b[1;32m    186\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 187\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mgeneration_method\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    188\u001b[0m     \u001b[38;5;66;03m# Do not retry for these errors.\u001b[39;00m\n\u001b[1;32m    189\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m google\u001b[38;5;241m.\u001b[39mapi_core\u001b[38;5;241m.\u001b[39mexceptions\u001b[38;5;241m.\u001b[39mFailedPrecondition \u001b[38;5;28;01mas\u001b[39;00m exc:\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/google/ai/generativelanguage_v1beta/services/generative_service/client.py:827\u001b[0m, in \u001b[0;36mGenerativeServiceClient.generate_content\u001b[0;34m(self, request, model, contents, retry, timeout, metadata)\u001b[0m\n\u001b[1;32m    824\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_universe_domain()\n\u001b[1;32m    826\u001b[0m \u001b[38;5;66;03m# Send the request.\u001b[39;00m\n\u001b[0;32m--> 827\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mrpc\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    828\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    829\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretry\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretry\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    830\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    831\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    832\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    834\u001b[0m \u001b[38;5;66;03m# Done; return the response.\u001b[39;00m\n\u001b[1;32m    835\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m response\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/google/api_core/gapic_v1/method.py:131\u001b[0m, in \u001b[0;36m_GapicCallable.__call__\u001b[0;34m(self, timeout, retry, compression, *args, **kwargs)\u001b[0m\n\u001b[1;32m    128\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compression \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    129\u001b[0m     kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcompression\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m compression\n\u001b[0;32m--> 131\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped_func\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/google/api_core/retry/retry_unary.py:293\u001b[0m, in \u001b[0;36mRetry.__call__.<locals>.retry_wrapped_func\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    289\u001b[0m target \u001b[38;5;241m=\u001b[39m functools\u001b[38;5;241m.\u001b[39mpartial(func, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m    290\u001b[0m sleep_generator \u001b[38;5;241m=\u001b[39m exponential_sleep_generator(\n\u001b[1;32m    291\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_initial, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_maximum, multiplier\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_multiplier\n\u001b[1;32m    292\u001b[0m )\n\u001b[0;32m--> 293\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mretry_target\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    294\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtarget\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    295\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_predicate\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    296\u001b[0m \u001b[43m    \u001b[49m\u001b[43msleep_generator\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    297\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_timeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    298\u001b[0m \u001b[43m    \u001b[49m\u001b[43mon_error\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mon_error\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    299\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/google/api_core/retry/retry_unary.py:153\u001b[0m, in \u001b[0;36mretry_target\u001b[0;34m(target, predicate, sleep_generator, timeout, on_error, exception_factory, **kwargs)\u001b[0m\n\u001b[1;32m    149\u001b[0m \u001b[38;5;66;03m# pylint: disable=broad-except\u001b[39;00m\n\u001b[1;32m    150\u001b[0m \u001b[38;5;66;03m# This function explicitly must deal with broad exceptions.\u001b[39;00m\n\u001b[1;32m    151\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[1;32m    152\u001b[0m     \u001b[38;5;66;03m# defer to shared logic for handling errors\u001b[39;00m\n\u001b[0;32m--> 153\u001b[0m     \u001b[43m_retry_error_helper\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    154\u001b[0m \u001b[43m        \u001b[49m\u001b[43mexc\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    155\u001b[0m \u001b[43m        \u001b[49m\u001b[43mdeadline\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    156\u001b[0m \u001b[43m        \u001b[49m\u001b[43msleep\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    157\u001b[0m \u001b[43m        \u001b[49m\u001b[43merror_list\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    158\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpredicate\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    159\u001b[0m \u001b[43m        \u001b[49m\u001b[43mon_error\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    160\u001b[0m \u001b[43m        \u001b[49m\u001b[43mexception_factory\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    161\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    162\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    163\u001b[0m     \u001b[38;5;66;03m# if exception not raised, sleep before next attempt\u001b[39;00m\n\u001b[1;32m    164\u001b[0m     time\u001b[38;5;241m.\u001b[39msleep(sleep)\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/google/api_core/retry/retry_base.py:212\u001b[0m, in \u001b[0;36m_retry_error_helper\u001b[0;34m(exc, deadline, next_sleep, error_list, predicate_fn, on_error_fn, exc_factory_fn, original_timeout)\u001b[0m\n\u001b[1;32m    206\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m predicate_fn(exc):\n\u001b[1;32m    207\u001b[0m     final_exc, source_exc \u001b[38;5;241m=\u001b[39m exc_factory_fn(\n\u001b[1;32m    208\u001b[0m         error_list,\n\u001b[1;32m    209\u001b[0m         RetryFailureReason\u001b[38;5;241m.\u001b[39mNON_RETRYABLE_ERROR,\n\u001b[1;32m    210\u001b[0m         original_timeout,\n\u001b[1;32m    211\u001b[0m     )\n\u001b[0;32m--> 212\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m final_exc \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msource_exc\u001b[39;00m\n\u001b[1;32m    213\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m on_error_fn \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    214\u001b[0m     on_error_fn(exc)\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/google/api_core/retry/retry_unary.py:144\u001b[0m, in \u001b[0;36mretry_target\u001b[0;34m(target, predicate, sleep_generator, timeout, on_error, exception_factory, **kwargs)\u001b[0m\n\u001b[1;32m    142\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m sleep \u001b[38;5;129;01min\u001b[39;00m sleep_generator:\n\u001b[1;32m    143\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 144\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[43mtarget\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    145\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m inspect\u001b[38;5;241m.\u001b[39misawaitable(result):\n\u001b[1;32m    146\u001b[0m             warnings\u001b[38;5;241m.\u001b[39mwarn(_ASYNC_RETRY_WARNING)\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/google/api_core/timeout.py:120\u001b[0m, in \u001b[0;36mTimeToDeadlineTimeout.__call__.<locals>.func_with_timeout\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    117\u001b[0m     \u001b[38;5;66;03m# Avoid setting negative timeout\u001b[39;00m\n\u001b[1;32m    118\u001b[0m     kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtimeout\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mmax\u001b[39m(\u001b[38;5;241m0\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_timeout \u001b[38;5;241m-\u001b[39m time_since_first_attempt)\n\u001b[0;32m--> 120\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/Projects/LocalRAG/.venv/lib/python3.10/site-packages/google/api_core/grpc_helpers.py:78\u001b[0m, in \u001b[0;36m_wrap_unary_errors.<locals>.error_remapped_callable\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m     76\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m callable_(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m     77\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m grpc\u001b[38;5;241m.\u001b[39mRpcError \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[0;32m---> 78\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m exceptions\u001b[38;5;241m.\u001b[39mfrom_grpc_error(exc) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mexc\u001b[39;00m\n",
-      "\u001b[0;31mResourceExhausted\u001b[0m: 429 Resource has been exhausted (e.g. check quota)."
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "prompt = \"\"\"\n",
-    "                  Please provide a summary of the following text.\n",
+    "                  Please provide a very comprehensive summary of the following text.\n",
+    "                  WHile maintaining lower level detail\n",
+    "                  \n",
     "                  TEXT: {text}\n",
     "                  SUMMARY:\n",
     "                  \"\"\"\n",
@@ -197,12 +138,15 @@
     ")\n",
     "\n",
     "refine_prompt_template = \"\"\"\n",
-    "              Write a concise summary of the following text delimited by triple backquotes.\n",
-    "              Return your response in bullet points which covers the key points of the text.\n",
+    "              Write a comprehensive summary of the following text delimited by triple backquotes.\n",
+    "              Your goal will be to give a high level overview while also expounding on some finer details of the text\n",
+    "\n",
     "              ```{text}```\n",
-    "              BULLET POINT SUMMARY:\n",
+    "              \n",
+    "            Have your answer in about 1500 words\n",
     "              \"\"\"\n",
     "\n",
+    "\n",
     "refine_template = PromptTemplate(\n",
     "    template=refine_prompt_template, input_variables=[\"text\"]\n",
     ")\n",
@@ -215,11 +159,67 @@
     "    refine_prompt=refine_template,\n",
     "    return_intermediate_steps=True,\n",
     "    input_key=\"input_documents\",\n",
-    "    output_key=\"output_text\",\n",
+    "    output_key=output_key,\n",
     ")\n",
     "result = chain({\"input_documents\": split_docs}, return_only_outputs=True)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import display, Markdown"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Here is a summary of the text:\n",
+       "\n",
+       "A state machine is a mathematical model that describes how an output signal is generated from an input signal step-by-step. It consists of five main components: \n",
+       "\n",
+       "1. States (representing different states or conditions)\n",
+       "2. Inputs (input signals, such as letters or symbols)\n",
+       "3. Outputs (output signals, which represent the actual output based on the input and state)\n",
+       "4. Update function (a way to modify the current state based on the inputs and outputs)\n",
+       "5. Initial State (the starting point of the machine)\n",
+       "\n",
+       "An example is given where a state machine is defined with three states: States, Inputs, Outputs. The initial state is also provided as an option.\n",
+       "\n",
+       "The key points are:\n",
+       "\n",
+       "* Time is not involved in this model; instead, step numbers refer to the order in which steps occur.\n",
+       "* Each input signal can be represented by an infinite sequence of symbols, such as a natural number sequence (e.g., 0 -> Inputs).\n",
+       "* The state machine evolves or \"moves\" from one state to another based on the inputs and outputs.\n",
+       "\n",
+       "This model is used for various applications, including control systems, data processing, and communication systems."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "display(Markdown(result[output_key]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

examples/tests/hf_login.py

@@ -4,10 +4,10 @@ from huggingface_hub import login
 import transformers, torch
 
 import os
-from huggingface_hub import HfApi
+# from huggingface_hub import HfApi
 
 # Get the token from the environment variable
-token = os.environ.get("HF_TOKEN_READ")
+token = os.getenv("HF_TOKEN_READ")
 
 print(token)