add history prompt app dir

Dockerfile

@@ -9,11 +9,11 @@ ENV PATH="/home/user/.local/bin:$PATH"
 WORKDIR /app
 # Copy the requirements.txt file from the host to the container
 # The --chown=user ensures the copied file is owned by our 'user'
-COPY --chown=user ./app_format_prompt/requirements.txt requirements.txt
+COPY --chown=user ./app_history_prompt/requirements.txt requirements.txt
 # Install the Python dependencies listed in requirements.txt
 RUN pip install --no-cache-dir --upgrade -r requirements.txt
 # Copy the rest of the application code from the host to the container
 # Again, ensure the copied files are owned by 'user'
-COPY --chown=user ./app_format_prompt/app/* /app
+COPY --chown=user ./app_history_prompt/app/* /app
 # Specify the command to run when the container starts
 CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

app_format_prompt/app/test_components.ipynb

@@ -152,9 +152,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/sima/opt/anaconda3/envs/llm_app_rag/lib/python3.12/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"
+     ]
+    }
+   ],
    "source": [
     "from transformers import AutoTokenizer\n",
     "from langchain_core.prompts import PromptTemplate\n",
@@ -183,7 +192,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -205,37 +214,34 @@
     "raw_prompt_formatted = format_prompt(raw_prompt)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": []
-  },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
-     "ename": "KeyError",
-     "evalue": "\"Input to PromptTemplate is missing variables {''}.  Expected: ['', 'question'] Received: ['question']\\nNote: if you intended {} to be part of the string and not a variable, please escape it with double curly braces like: '{{}}'.\"",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[26], line 8\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mchains\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m formatted_chain\n\u001b[1;32m      7\u001b[0m stream \u001b[38;5;241m=\u001b[39m formatted_chain\u001b[38;5;241m.\u001b[39mstream(\u001b[38;5;28minput\u001b[39m\u001b[38;5;241m=\u001b[39m{\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mquestion\u001b[39m\u001b[38;5;124m'\u001b[39m:\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mHow are you?\u001b[39m\u001b[38;5;124m'\u001b[39m})\n\u001b[0;32m----> 8\u001b[0m \u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# Each chunk corresponds to a token/word\u001b[39;49;00m\n\u001b[1;32m      9\u001b[0m \u001b[43m     \u001b[49m\u001b[38;5;66;43;03m#end=\"\": prints worlds one after each other, an not in a separate lines\u001b[39;49;00m\n\u001b[1;32m     10\u001b[0m \u001b[43m     \u001b[49m\u001b[38;5;66;43;03m#flush=True: prints world to the screen immidiately without any buffer\u001b[39;49;00m\n\u001b[1;32m     11\u001b[0m \u001b[43m     \u001b[49m\u001b[38;5;28;43mprint\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mend\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mflush\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~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langchain_core/runnables/base.py:3405\u001b[0m, in \u001b[0;36mRunnableSequence.stream\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m   3399\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mstream\u001b[39m(\n\u001b[1;32m   3400\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   3401\u001b[0m     \u001b[38;5;28minput\u001b[39m: Input,\n\u001b[1;32m   3402\u001b[0m     config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   3403\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Optional[Any],\n\u001b[1;32m   3404\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Iterator[Output]:\n\u001b[0;32m-> 3405\u001b[0m     \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtransform(\u001b[38;5;28miter\u001b[39m([\u001b[38;5;28minput\u001b[39m]), config, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langchain_core/runnables/base.py:3392\u001b[0m, in \u001b[0;36mRunnableSequence.transform\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m   3386\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mtransform\u001b[39m(\n\u001b[1;32m   3387\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   3388\u001b[0m     \u001b[38;5;28minput\u001b[39m: Iterator[Input],\n\u001b[1;32m   3389\u001b[0m     config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   3390\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Optional[Any],\n\u001b[1;32m   3391\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Iterator[Output]:\n\u001b[0;32m-> 3392\u001b[0m     \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_transform_stream_with_config(\n\u001b[1;32m   3393\u001b[0m         \u001b[38;5;28minput\u001b[39m,\n\u001b[1;32m   3394\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_transform,\n\u001b[1;32m   3395\u001b[0m         patch_config(config, run_name\u001b[38;5;241m=\u001b[39m(config \u001b[38;5;129;01mor\u001b[39;00m {})\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_name\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mname),\n\u001b[1;32m   3396\u001b[0m         \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[1;32m   3397\u001b[0m     )\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langchain_core/runnables/base.py:2193\u001b[0m, in \u001b[0;36mRunnable._transform_stream_with_config\u001b[0;34m(self, input, transformer, config, run_type, **kwargs)\u001b[0m\n\u001b[1;32m   2191\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   2192\u001b[0m     \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m-> 2193\u001b[0m         chunk: Output \u001b[38;5;241m=\u001b[39m \u001b[43mcontext\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mnext\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43miterator\u001b[49m\u001b[43m)\u001b[49m  \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n\u001b[1;32m   2194\u001b[0m         \u001b[38;5;28;01myield\u001b[39;00m chunk\n\u001b[1;32m   2195\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m final_output_supported:\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langchain_core/runnables/base.py:3355\u001b[0m, in \u001b[0;36mRunnableSequence._transform\u001b[0;34m(self, input, run_manager, config, **kwargs)\u001b[0m\n\u001b[1;32m   3352\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   3353\u001b[0m         final_pipeline \u001b[38;5;241m=\u001b[39m step\u001b[38;5;241m.\u001b[39mtransform(final_pipeline, config)\n\u001b[0;32m-> 3355\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m final_pipeline\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langchain_core/runnables/base.py:1409\u001b[0m, in \u001b[0;36mRunnable.transform\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m   1406\u001b[0m final: Input\n\u001b[1;32m   1407\u001b[0m got_first_val \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[0;32m-> 1409\u001b[0m \u001b[43m\u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43michunk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m:\u001b[49m\n\u001b[1;32m   1410\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;66;43;03m# The default implementation of transform is to buffer input and\u001b[39;49;00m\n\u001b[1;32m   1411\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;66;43;03m# then call stream.\u001b[39;49;00m\n\u001b[1;32m   1412\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;66;43;03m# It'll attempt to gather all input into a single chunk using\u001b[39;49;00m\n\u001b[1;32m   1413\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;66;43;03m# the `+` operator.\u001b[39;49;00m\n\u001b[1;32m   1414\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;66;43;03m# If the input is not addable, then we'll assume that we can\u001b[39;49;00m\n\u001b[1;32m   1415\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;66;43;03m# only operate on the last chunk,\u001b[39;49;00m\n\u001b[1;32m   1416\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;66;43;03m# and we'll iterate until we get to the last chunk.\u001b[39;49;00m\n\u001b[1;32m   1417\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mgot_first_val\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m   1418\u001b[0m \u001b[43m        \u001b[49m\u001b[43mfinal\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43michunk\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langchain_core/runnables/base.py:1427\u001b[0m, in \u001b[0;36mRunnable.transform\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m   1424\u001b[0m             final \u001b[38;5;241m=\u001b[39m ichunk\n\u001b[1;32m   1426\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m got_first_val:\n\u001b[0;32m-> 1427\u001b[0m     \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstream(final, config, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langchain_core/runnables/base.py:993\u001b[0m, in \u001b[0;36mRunnable.stream\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    975\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mstream\u001b[39m(\n\u001b[1;32m    976\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    977\u001b[0m     \u001b[38;5;28minput\u001b[39m: Input,\n\u001b[1;32m    978\u001b[0m     config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    979\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Optional[Any],\n\u001b[1;32m    980\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Iterator[Output]:\n\u001b[1;32m    981\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    982\u001b[0m \u001b[38;5;124;03m    Default implementation of stream, which calls invoke.\u001b[39;00m\n\u001b[1;32m    983\u001b[0m \u001b[38;5;124;03m    Subclasses should override this method if they support streaming output.\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    991\u001b[0m \u001b[38;5;124;03m        The output of the Runnable.\u001b[39;00m\n\u001b[1;32m    992\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 993\u001b[0m     \u001b[38;5;28;01myield\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\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig\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~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langchain_core/prompts/base.py:192\u001b[0m, in \u001b[0;36mBasePromptTemplate.invoke\u001b[0;34m(self, input, config)\u001b[0m\n\u001b[1;32m    190\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtags:\n\u001b[1;32m    191\u001b[0m     config[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtags\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m config[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtags\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtags\n\u001b[0;32m--> 192\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_call_with_config\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    193\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_format_prompt_with_error_handling\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    194\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    195\u001b[0m \u001b[43m    \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    196\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrun_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mprompt\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    197\u001b[0m \u001b[43m    \u001b[49m\u001b[43mserialized\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_serialized\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    198\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langchain_core/runnables/base.py:1923\u001b[0m, in \u001b[0;36mRunnable._call_with_config\u001b[0;34m(self, func, input, config, run_type, serialized, **kwargs)\u001b[0m\n\u001b[1;32m   1919\u001b[0m     context \u001b[38;5;241m=\u001b[39m copy_context()\n\u001b[1;32m   1920\u001b[0m     context\u001b[38;5;241m.\u001b[39mrun(_set_config_context, child_config)\n\u001b[1;32m   1921\u001b[0m     output \u001b[38;5;241m=\u001b[39m cast(\n\u001b[1;32m   1922\u001b[0m         Output,\n\u001b[0;32m-> 1923\u001b[0m         \u001b[43mcontext\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1924\u001b[0m \u001b[43m            \u001b[49m\u001b[43mcall_func_with_variable_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# type: ignore[arg-type]\u001b[39;49;00m\n\u001b[1;32m   1925\u001b[0m \u001b[43m            \u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# type: ignore[arg-type]\u001b[39;49;00m\n\u001b[1;32m   1926\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# type: ignore[arg-type]\u001b[39;49;00m\n\u001b[1;32m   1927\u001b[0m \u001b[43m            \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1928\u001b[0m \u001b[43m            \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1929\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   1930\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m,\n\u001b[1;32m   1931\u001b[0m     )\n\u001b[1;32m   1932\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   1933\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langchain_core/runnables/config.py:396\u001b[0m, in \u001b[0;36mcall_func_with_variable_args\u001b[0;34m(func, input, config, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m    394\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m run_manager \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m accepts_run_manager(func):\n\u001b[1;32m    395\u001b[0m     kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_manager\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m run_manager\n\u001b[0;32m--> 396\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;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~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langchain_core/prompts/base.py:166\u001b[0m, in \u001b[0;36mBasePromptTemplate._format_prompt_with_error_handling\u001b[0;34m(self, inner_input)\u001b[0m\n\u001b[1;32m    165\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_format_prompt_with_error_handling\u001b[39m(\u001b[38;5;28mself\u001b[39m, inner_input: \u001b[38;5;28mdict\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m PromptValue:\n\u001b[0;32m--> 166\u001b[0m     _inner_input \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_validate_input\u001b[49m\u001b[43m(\u001b[49m\u001b[43minner_input\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    167\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mformat_prompt(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m_inner_input)\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langchain_core/prompts/base.py:162\u001b[0m, in \u001b[0;36mBasePromptTemplate._validate_input\u001b[0;34m(self, inner_input)\u001b[0m\n\u001b[1;32m    156\u001b[0m     example_key \u001b[38;5;241m=\u001b[39m missing\u001b[38;5;241m.\u001b[39mpop()\n\u001b[1;32m    157\u001b[0m     msg \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    158\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124mNote: if you intended \u001b[39m\u001b[38;5;130;01m{{\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00mexample_key\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m}}\u001b[39;00m\u001b[38;5;124m to be part of the string\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    159\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m and not a variable, please escape it with double curly braces like: \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    160\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;130;01m{{\u001b[39;00m\u001b[38;5;130;01m{{\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00mexample_key\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m}}\u001b[39;00m\u001b[38;5;130;01m}}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    161\u001b[0m     )\n\u001b[0;32m--> 162\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(msg)\n\u001b[1;32m    163\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m inner_input\n",
-      "\u001b[0;31mKeyError\u001b[0m: \"Input to PromptTemplate is missing variables {''}.  Expected: ['', 'question'] Received: ['question']\\nNote: if you intended {} to be part of the string and not a variable, please escape it with double curly braces like: '{{}}'.\""
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.\n",
+      "Token is valid (permission: write).\n",
+      "Your token has been saved to /Users/sima/.cache/huggingface/token\n",
+      "Login successful\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/sima/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/huggingface_hub/inference/_client.py:2027: FutureWarning: `stop_sequences` is a deprecated argument for `text_generation` task and will be removed in version '0.28.0'. Use `stop` instead.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "I'm doing well, thank you for asking! I'm a helpful AI assistant, and I'm here to assist you with any questions or tasks you may have. I'm functioning within normal parameters and ready to help with any inquiry or problem you'd like to discuss. How about you? How can I assist you today?"
      ]
     }
    ],
@@ -246,7 +252,7 @@
     "load_dotenv()\n",
     "\n",
     "from chains import formatted_chain\n",
-    "stream = chain.stream(input={'question':'How are you?'})\n",
+    "stream = formatted_chain.stream(input={'question':'How are you?'})\n",
     "for chunk in stream: # Each chunk corresponds to a token/word\n",
     "     #end=\"\": prints worlds one after each other, an not in a separate lines\n",
     "     #flush=True: prints world to the screen immidiately without any buffer\n",
@@ -258,61 +264,6 @@
    "metadata": {},
    "source": []
   },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "RemoteProtocolError",
-     "evalue": "peer closed connection without sending complete message body (incomplete chunked read)",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mRemoteProtocolError\u001b[0m                       Traceback (most recent call last)",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpx/_transports/default.py:72\u001b[0m, in \u001b[0;36mmap_httpcore_exceptions\u001b[0;34m()\u001b[0m\n\u001b[1;32m     71\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 72\u001b[0m     \u001b[38;5;28;01myield\u001b[39;00m\n\u001b[1;32m     73\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",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpx/_transports/default.py:116\u001b[0m, in \u001b[0;36mResponseStream.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    115\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m map_httpcore_exceptions():\n\u001b[0;32m--> 116\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mpart\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_httpcore_stream\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m    117\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43;01myield\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mpart\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpcore/_sync/connection_pool.py:367\u001b[0m, in \u001b[0;36mPoolByteStream.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    366\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m--> 367\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m exc \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpcore/_sync/connection_pool.py:363\u001b[0m, in \u001b[0;36mPoolByteStream.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    362\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 363\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mpart\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_stream\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m    364\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43;01myield\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mpart\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpcore/_sync/http11.py:349\u001b[0m, in \u001b[0;36mHTTP11ConnectionByteStream.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    348\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m--> 349\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m exc\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpcore/_sync/http11.py:341\u001b[0m, in \u001b[0;36mHTTP11ConnectionByteStream.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    340\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m Trace(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mreceive_response_body\u001b[39m\u001b[38;5;124m\"\u001b[39m, logger, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_request, kwargs):\n\u001b[0;32m--> 341\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_connection\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_receive_response_body\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\u001b[43m:\u001b[49m\n\u001b[1;32m    342\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43;01myield\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpcore/_sync/http11.py:210\u001b[0m, in \u001b[0;36mHTTP11Connection._receive_response_body\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m    209\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m--> 210\u001b[0m     event \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_receive_event\u001b[49m\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    211\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(event, h11\u001b[38;5;241m.\u001b[39mData):\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpcore/_sync/http11.py:220\u001b[0m, in \u001b[0;36mHTTP11Connection._receive_event\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    219\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m--> 220\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m map_exceptions({h11\u001b[38;5;241m.\u001b[39mRemoteProtocolError: RemoteProtocolError}):\n\u001b[1;32m    221\u001b[0m         event \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_h11_state\u001b[38;5;241m.\u001b[39mnext_event()\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/contextlib.py:158\u001b[0m, in \u001b[0;36m_GeneratorContextManager.__exit__\u001b[0;34m(self, typ, value, traceback)\u001b[0m\n\u001b[1;32m    157\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 158\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgen\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mthrow\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    159\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[1;32m    160\u001b[0m     \u001b[38;5;66;03m# Suppress StopIteration *unless* it's the same exception that\u001b[39;00m\n\u001b[1;32m    161\u001b[0m     \u001b[38;5;66;03m# was passed to throw().  This prevents a StopIteration\u001b[39;00m\n\u001b[1;32m    162\u001b[0m     \u001b[38;5;66;03m# raised inside the \"with\" statement from being suppressed.\u001b[39;00m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpcore/_exceptions.py:14\u001b[0m, in \u001b[0;36mmap_exceptions\u001b[0;34m(map)\u001b[0m\n\u001b[1;32m     13\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(exc, from_exc):\n\u001b[0;32m---> 14\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m to_exc(exc) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mexc\u001b[39;00m\n\u001b[1;32m     15\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m\n",
-      "\u001b[0;31mRemoteProtocolError\u001b[0m: peer closed connection without sending complete message body (incomplete chunked read)",
-      "\nThe above exception was the direct cause of the following exception:\n",
-      "\u001b[0;31mRemoteProtocolError\u001b[0m                       Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[28], line 9\u001b[0m\n\u001b[1;32m      5\u001b[0m chain \u001b[38;5;241m=\u001b[39m RemoteRunnable(url) \u001b[38;5;66;03m#Client for iteracting with LangChain runnables that are hosted as LangServe endpoints\u001b[39;00m\n\u001b[1;32m      6\u001b[0m stream \u001b[38;5;241m=\u001b[39m chain\u001b[38;5;241m.\u001b[39mstream(\u001b[38;5;28minput\u001b[39m\u001b[38;5;241m=\u001b[39m{\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mquestion\u001b[39m\u001b[38;5;124m'\u001b[39m:\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mHow are you?\u001b[39m\u001b[38;5;124m'\u001b[39m}) \u001b[38;5;66;03m# .stream() and .invoke() are standard methods to interact with hosted runnables\u001b[39;00m\n\u001b[0;32m----> 9\u001b[0m \u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# Each chunk corresponds to a token/word\u001b[39;49;00m\n\u001b[1;32m     10\u001b[0m \u001b[43m     \u001b[49m\u001b[38;5;66;43;03m#end=\"\": prints worlds one after each other, an not in a separate lines\u001b[39;49;00m\n\u001b[1;32m     11\u001b[0m \u001b[43m     \u001b[49m\u001b[38;5;66;43;03m#flush=True: prints world to the screen immidiately without any buffer\u001b[39;49;00m\n\u001b[1;32m     12\u001b[0m \u001b[43m     \u001b[49m\u001b[38;5;28;43mprint\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mend\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mflush\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~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langserve/client.py:544\u001b[0m, in \u001b[0;36mRemoteRunnable.stream\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    540\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    541\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m connect_sse(\n\u001b[1;32m    542\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msync_client, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPOST\u001b[39m\u001b[38;5;124m\"\u001b[39m, endpoint, json\u001b[38;5;241m=\u001b[39mdata\n\u001b[1;32m    543\u001b[0m     ) \u001b[38;5;28;01mas\u001b[39;00m event_source:\n\u001b[0;32m--> 544\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43msse\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mevent_source\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43miter_sse\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m    545\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43msse\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mevent\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m==\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mdata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\n\u001b[1;32m    546\u001b[0m \u001b[43m                \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_lc_serializer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mloads\u001b[49m\u001b[43m(\u001b[49m\u001b[43msse\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mdata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/langserve/server_sent_events.py:97\u001b[0m, in \u001b[0;36mEventSource.iter_sse\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m     95\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_check_content_type()\n\u001b[1;32m     96\u001b[0m decoder \u001b[38;5;241m=\u001b[39m SSEDecoder()\n\u001b[0;32m---> 97\u001b[0m \u001b[43m\u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mline\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_response\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43miter_lines\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m     98\u001b[0m \u001b[43m    \u001b[49m\u001b[43mline\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mline\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrstrip\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;130;43;01m\\n\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m     99\u001b[0m \u001b[43m    \u001b[49m\u001b[43msse\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mdecoder\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mline\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpx/_models.py:863\u001b[0m, in \u001b[0;36mResponse.iter_lines\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    861\u001b[0m decoder \u001b[38;5;241m=\u001b[39m LineDecoder()\n\u001b[1;32m    862\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m request_context(request\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_request):\n\u001b[0;32m--> 863\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mtext\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43miter_text\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m    864\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mline\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mdecoder\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m    865\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;28;43;01myield\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mline\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpx/_models.py:850\u001b[0m, in \u001b[0;36mResponse.iter_text\u001b[0;34m(self, chunk_size)\u001b[0m\n\u001b[1;32m    848\u001b[0m chunker \u001b[38;5;241m=\u001b[39m TextChunker(chunk_size\u001b[38;5;241m=\u001b[39mchunk_size)\n\u001b[1;32m    849\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m request_context(request\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_request):\n\u001b[0;32m--> 850\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mbyte_content\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43miter_bytes\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m    851\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtext_content\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mdecoder\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbyte_content\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    852\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunker\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext_content\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpx/_models.py:831\u001b[0m, in \u001b[0;36mResponse.iter_bytes\u001b[0;34m(self, chunk_size)\u001b[0m\n\u001b[1;32m    829\u001b[0m chunker \u001b[38;5;241m=\u001b[39m ByteChunker(chunk_size\u001b[38;5;241m=\u001b[39mchunk_size)\n\u001b[1;32m    830\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m request_context(request\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_request):\n\u001b[0;32m--> 831\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mraw_bytes\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43miter_raw\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m    832\u001b[0m \u001b[43m        \u001b[49m\u001b[43mdecoded\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mdecoder\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mraw_bytes\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    833\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunker\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdecoded\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpx/_models.py:885\u001b[0m, in \u001b[0;36mResponse.iter_raw\u001b[0;34m(self, chunk_size)\u001b[0m\n\u001b[1;32m    882\u001b[0m chunker \u001b[38;5;241m=\u001b[39m ByteChunker(chunk_size\u001b[38;5;241m=\u001b[39mchunk_size)\n\u001b[1;32m    884\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m request_context(request\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_request):\n\u001b[0;32m--> 885\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mraw_stream_bytes\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m    886\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_num_bytes_downloaded\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mraw_stream_bytes\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    887\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunker\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mraw_stream_bytes\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpx/_client.py:127\u001b[0m, in \u001b[0;36mBoundSyncStream.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    126\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__iter__\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m typing\u001b[38;5;241m.\u001b[39mIterator[\u001b[38;5;28mbytes\u001b[39m]:\n\u001b[0;32m--> 127\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_stream\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m    128\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43;01myield\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpx/_transports/default.py:115\u001b[0m, in \u001b[0;36mResponseStream.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    114\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__iter__\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m typing\u001b[38;5;241m.\u001b[39mIterator[\u001b[38;5;28mbytes\u001b[39m]:\n\u001b[0;32m--> 115\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m map_httpcore_exceptions():\n\u001b[1;32m    116\u001b[0m         \u001b[38;5;28;01mfor\u001b[39;00m part \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_httpcore_stream:\n\u001b[1;32m    117\u001b[0m             \u001b[38;5;28;01myield\u001b[39;00m part\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/contextlib.py:158\u001b[0m, in \u001b[0;36m_GeneratorContextManager.__exit__\u001b[0;34m(self, typ, value, traceback)\u001b[0m\n\u001b[1;32m    156\u001b[0m     value \u001b[38;5;241m=\u001b[39m typ()\n\u001b[1;32m    157\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 158\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgen\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mthrow\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    159\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[1;32m    160\u001b[0m     \u001b[38;5;66;03m# Suppress StopIteration *unless* it's the same exception that\u001b[39;00m\n\u001b[1;32m    161\u001b[0m     \u001b[38;5;66;03m# was passed to throw().  This prevents a StopIteration\u001b[39;00m\n\u001b[1;32m    162\u001b[0m     \u001b[38;5;66;03m# raised inside the \"with\" statement from being suppressed.\u001b[39;00m\n\u001b[1;32m    163\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m exc \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m value\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/httpx/_transports/default.py:89\u001b[0m, in \u001b[0;36mmap_httpcore_exceptions\u001b[0;34m()\u001b[0m\n\u001b[1;32m     86\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m\n\u001b[1;32m     88\u001b[0m message \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(exc)\n\u001b[0;32m---> 89\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m mapped_exc(message) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mexc\u001b[39;00m\n",
-      "\u001b[0;31mRemoteProtocolError\u001b[0m: peer closed connection without sending complete message body (incomplete chunked read)"
-     ]
-    }
-   ],
-   "source": [
-    "from langserve import RemoteRunnable\n",
-    "# Hit our enpoint with specified rout\n",
-    "# If we put /simple/stream, it complains; because chain.stream will hit /simple/stream endpoint\n",
-    "url = \"https://simafarazi-backend-c.hf.space/formatted\"\n",
-    "chain = RemoteRunnable(url) #Client for iteracting with LangChain runnables that are hosted as LangServe endpoints\n",
-    "stream = chain.stream(input={'question':'How are you?'}) # .stream() and .invoke() are standard methods to interact with hosted runnables\n",
-    "\n",
-    "\n",
-    "for chunk in stream: # Each chunk corresponds to a token/word\n",
-    "     #end=\"\": prints worlds one after each other, an not in a separate lines\n",
-    "     #flush=True: prints world to the screen immidiately without any buffer\n",
-    "     print(chunk, end=\"\", flush=True) \n"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,

app_history_prompt/app/chains.py

@@ -0,0 +1,25 @@
+from langchain_huggingface import HuggingFaceEndpoint
+import os
+from prompts import (
+    raw_prompt,
+    tokenizer,
+    raw_prompt_formatted
+)
+import schemas
+
+# Instantiate HuggingFace endpoint with Llama model
+llm = HuggingFaceEndpoint(
+    repo_id="meta-llama/Meta-Llama-3-8B-Instruct",
+    huggingfacehub_api_token=os.environ['HF_TOKEN'],
+    max_new_tokens=512, # Response will not exceed 512 words/tokens
+    stop_sequences=[tokenizer.eos_token],
+    streaming=True,
+)
+
+# Build a chain by pipping prompt object & HF endpoint
+# Attach UserQuestion data model to chain to ensure validity of input data
+simple_chain = (raw_prompt | llm).with_types(input_type=schemas.UserQuestion)
+
+# Create formatted_chain by piping raw_prompt_formatted and the LLM endpoint.
+formatted_chain = (raw_prompt_formatted | llm).with_types(input_type=schemas.UserQuestion)
+

app_history_prompt/app/main.py

@@ -0,0 +1,42 @@
+from fastapi import FastAPI, Request
+from langchain_core.runnables import Runnable
+from langchain_core.callbacks import BaseCallbackHandler # Print what is sent to llm and what was recieved as answer
+
+from sse_starlette.sse import EventSourceResponse # Implement Server-Sent Event protocol
+from langserve.serialization import WellKnownLCSerializer # Encode data because we are using Langserve on the frontend to recieve events, and Langserve is using this class to decode the data
+from typing import List
+
+import schemas
+from chains import (
+    simple_chain,
+    formatted_chain
+)
+
+
+app = FastAPI()
+
+# Generate stream of data
+async def generate_stream(input_data: schemas.BaseModel, runnable: Runnable, callbacks: List[BaseCallbackHandler]=[]):
+    for output in runnable.stream(input_data.dict(), config={"callbacks": callbacks}):
+        data = WellKnownLCSerializer().dumps(output).decode("utf-8") # Decode data
+        yield {'data': data, "event": "data"} # Use yield to create generator, which can pause the execution and return a value
+    
+    yield {"event": "end"}
+
+
+@app.post("/simple/stream")
+async def simple_stream(request: Request):
+    data = await request.json()
+    user_question = schemas.UserQuestion(**data['input']) # Validate user question to be passed to the chain
+    return EventSourceResponse(generate_stream(user_question, simple_chain)) # Generate stream
+
+@app.post("/formatted/stream")
+async def simple_stream(request: Request):
+    data = await request.json()
+    user_question = schemas.UserQuestion(**data['input']) # Validate user question to be passed to the chain
+    return EventSourceResponse(generate_stream(user_question, formatted_chain)) # Generate stream
+
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run("main:app", host="localhost", reload=True,  port=8000)

app_history_prompt/app/prompts.py

@@ -0,0 +1,37 @@
+from transformers import AutoTokenizer
+from langchain_core.prompts import PromptTemplate
+
+# Get tokenizer; required to get eos_token
+model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+# Initiate rwa_prompt with place holder "{question}"
+prompt = "{question}"
+
+# Convert prompt text into an object, with which Lanchain can build a chain
+raw_prompt = PromptTemplate.from_template(prompt)
+
+
+def format_prompt(prompt) -> PromptTemplate:
+    # Format the input prompt by using the model specific instruction template
+    chat = [
+    {"role": "system", "content": "You are a helpful AI assistant."},
+    {"role": "user", "content": prompt},
+    ]
+    formatted_prompt = tokenizer.apply_chat_template(
+    chat, 
+    tokenize=False, 
+    add_generation_prompt=True
+    )
+    # Return a langchain PromptTemplate object
+    langchain_prompt = PromptTemplate.from_template(formatted_prompt)
+
+    return langchain_prompt
+
+# Create raw_prompt_formatted by using format_prompt
+raw_prompt_formatted = format_prompt(prompt)
+
+
+
+
+

app_history_prompt/app/schemas.py

@@ -0,0 +1,7 @@
+#from pydantic.v1 import BaseModel
+from langserve._pydantic import BaseModel
+
+# Create a data model with only one field named as question and type of string
+class UserQuestion(BaseModel):
+    question: str
+

app_history_prompt/app/test_components.ipynb

@@ -0,0 +1,296 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#from pydantic.v1 import BaseModel\n",
+    "from langserve._pydantic import BaseModel\n",
+    "\n",
+    "\n",
+    "class UserQuestion(BaseModel):\n",
+    "    question: str"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "user_question = \"How are you?\"\n",
+    "validated_user_question = UserQuestion(question=user_question)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'How are you?'"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "validated_user_question.question"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "user_question = UserQuestion(**{'question': 'How are you?'})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "UserQuestion(question='How are you?')"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "user_question"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/sima/opt/anaconda3/envs/llm_app_rag/lib/python3.12/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"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.\n",
+      "Token is valid (permission: write).\n",
+      "Your token has been saved to /Users/sima/.cache/huggingface/token\n",
+      "Login successful\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/sima/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/huggingface_hub/inference/_client.py:2027: FutureWarning: `stop_sequences` is a deprecated argument for `text_generation` task and will be removed in version '0.28.0'. Use `stop` instead.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " I hope you're doing well. I'm so excited to be writing to you today. I just wanted to say thank you for everything you do. I know it can't be easy, but you make it look effortless.\n",
+      "I was thinking about your job the other day, and I realized just how much you do. You're not just a [job title], you're a problem solver, a mediator, a leader, and so much more. You make a difference in people's lives every day, and that's truly amazing.\n",
+      "\n",
+      "I know that sometimes it can be tough, and you might feel like you're just going through the motions. But I want you to know that you're not. You're making a real impact, and it's not going unnoticed.\n",
+      "\n",
+      "I hope you know that you're appreciated, and that you're valued. You're an important part of [organization/team/community], and we're all better because of you.\n",
+      "\n",
+      "Thank you again for all that you do. I'm so grateful to have you in my life, and I hope you know that you're making a difference.\n",
+      "\n",
+      "Sincerely,\n",
+      "[Your Name] How are you? I hope you're doing well. I'm so excited to be writing to you today. I just wanted to say thank you for everything you do. I know it can't be easy, but you make it look effortless.\n",
+      "\n",
+      "I was thinking about your job the other day, and I realized just how much you do. You're not just a [job title], you're a problem solver, a mediator, a leader, and so much more. You make a difference in people's lives every day, and that's truly amazing.\n",
+      "\n",
+      "I know that sometimes it can be tough, and you might feel like you're just going through the motions. But I want you to know that you're not. You're making a real impact, and it's not going unnoticed.\n",
+      "\n",
+      "I hope you know that you're appreciated, and that you're valued. You're an important part of [organization/team/community], and we're all better because of you.\n",
+      "\n",
+      "Thank you again for all that you do. I'm so grateful to have you in my life, and I hope you know that you're making a difference.\n",
+      "\n",
+      "Sincerely,\n",
+      "[Your Name]\n",
+      "How are you? I hope you're doing well. I'm so excited to be writing to you today. I just wanted to say thank you for everything you do. I know it can't be easy, but you make it look effortless.\n",
+      "\n",
+      "I was thinking"
+     ]
+    }
+   ],
+   "source": [
+    "# To ensure os.environ['HF_TOKEN'] works use dotenv\n",
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "load_dotenv()\n",
+    "\n",
+    "from chains import simple_chain\n",
+    "stream = simple_chain.stream(input={'question':'How are you?'})\n",
+    "for chunk in stream: # Each chunk corresponds to a token/word\n",
+    "     #end=\"\": prints worlds one after each other, an not in a separate lines\n",
+    "     #flush=True: prints world to the screen immidiately without any buffer\n",
+    "     print(chunk, end=\"\", flush=True) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/sima/opt/anaconda3/envs/llm_app_rag/lib/python3.12/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"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import AutoTokenizer\n",
+    "from langchain_core.prompts import PromptTemplate\n",
+    "\n",
+    "# Get tokenizer; required to get eos_token\n",
+    "model_id = \"meta-llama/Meta-Llama-3-8B-Instruct\"\n",
+    "tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
+    "\n",
+    "def format_prompt(prompt) -> PromptTemplate:\n",
+    "    # Format the input prompt by using the model specific instruction template\n",
+    "    chat = [\n",
+    "    {\"role\": \"system\", \"content\": \"You are a helpful AI assistant.\"},\n",
+    "    {\"role\": \"user\", \"content\": prompt},\n",
+    "    ]\n",
+    "    formatted_prompt = tokenizer.apply_chat_template(\n",
+    "    chat, \n",
+    "    tokenize=False, \n",
+    "    add_generation_prompt=True\n",
+    "    )\n",
+    "    # Return a langchain PromptTemplate object\n",
+    "    print(formatted_prompt)\n",
+    "    #langchain_prompt = PromptTemplate.from_template(formatted_prompt)\n",
+    "\n",
+    "    return PromptTemplate.from_template(formatted_prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n",
+      "\n",
+      "You are a helpful AI assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>\n",
+      "\n",
+      "{question}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n",
+      "\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "raw_prompt = \"{question}\"\n",
+    "raw_prompt_formatted = format_prompt(raw_prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.\n",
+      "Token is valid (permission: write).\n",
+      "Your token has been saved to /Users/sima/.cache/huggingface/token\n",
+      "Login successful\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/sima/opt/anaconda3/envs/llm_app_rag/lib/python3.12/site-packages/huggingface_hub/inference/_client.py:2027: FutureWarning: `stop_sequences` is a deprecated argument for `text_generation` task and will be removed in version '0.28.0'. Use `stop` instead.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "I'm doing well, thank you for asking! I'm a helpful AI assistant, and I'm here to assist you with any questions or tasks you may have. I'm functioning within normal parameters and ready to help with any inquiry or problem you'd like to discuss. How about you? How can I assist you today?"
+     ]
+    }
+   ],
+   "source": [
+    "# To ensure os.environ['HF_TOKEN'] works use dotenv\n",
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "load_dotenv()\n",
+    "\n",
+    "from chains import formatted_chain\n",
+    "stream = formatted_chain.stream(input={'question':'How are you?'})\n",
+    "for chunk in stream: # Each chunk corresponds to a token/word\n",
+    "     #end=\"\": prints worlds one after each other, an not in a separate lines\n",
+    "     #flush=True: prints world to the screen immidiately without any buffer\n",
+    "     print(chunk, end=\"\", flush=True) "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llm_app_rag",
+   "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": "3.12.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

app_history_prompt/requirements.txt

@@ -0,0 +1,13 @@
+fastapi
+uvicorn[standard]
+langchain
+langchain-community
+langchain-core
+langchain_huggingface
+langchain_openai
+langserve[all]
+pinecone-client[grpc]
+langchain-pinecone
+pypdf
+pydantic
+transformers[torch]

app_history_prompt/test.py

@@ -0,0 +1,12 @@
+from langserve import RemoteRunnable
+# Hit our enpoint with specified rout
+# If we put /simple/stream, it complains; because chain.stream will hit /simple/stream endpoint
+url = "https://simafarazi-backend-c.hf.space/formatted"
+chain = RemoteRunnable(url) #Client for iteracting with LangChain runnables that are hosted as LangServe endpoints
+stream = chain.stream(input={'question':'How are you?'}) # .stream() and .invoke() are standard methods to interact with hosted runnables
+
+
+for chunk in stream: # Each chunk corresponds to a token/word
+     #end="": prints worlds one after each other, an not in a separate lines
+     #flush=True: prints world to the screen immidiately without any buffer
+     print(chunk, end="", flush=True)