Pre-deployment non-lfs changes

.gitattributes

@@ -0,0 +1,36 @@
+*.sqlite3 filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1,5 +1,8 @@
-scripts/db/
-wookieepedia/db/
+# Track db subfolders but the files in their containing folders
+scripts/*
+!scripts/db/
+wookieepedia/*
+!wookieepedia/db/
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

app.py

@@ -0,0 +1,71 @@
+# Chains
+from langchain_core.pydantic_v1 import BaseModel, Field
+
+# To serve the app
+from fastapi import FastAPI
+from langchain_core.messages import BaseMessage
+from langserve import add_routes, CustomUserType
+
+import dotenv
+dotenv.load_dotenv()
+
+from ingredients import script_db, woo_db, full_chain, compound_chain, agent_executor
+
+
+
+## Type specifications (with unusual class-scope fields)
+
+class StrInput(BaseModel):
+    input: str
+
+class Input(BaseModel):
+    input: str
+    chat_history: list[BaseMessage] = Field(
+        ...,
+        extra = dict(widget = dict(type = 'chat', input = 'location')),
+    )
+
+class Output(BaseModel):
+    output: str
+
+
+
+## App definition
+# NOTE: The chat playground type has a web page issue (flashes and becomes white, hence non-interactable; this was supposedly solved in an issue late last year)
+
+app = FastAPI(
+    title = 'Star Wars Expert',
+    version = '1.0',
+    description = 'A Star Wars expert chatbot',
+)
+
+
+# Basic retriever versions
+
+# add_routes(app, script_db.as_retriever())
+# add_routes(app, woo_db.as_retriever())
+
+
+# History-aware retriever version
+# add_routes(app, full_chain.with_types(input_type = StrInput, output_type = Output), playground_type = 'default')
+
+
+# Agent version
+
+# add_routes(app, agent_executor, playground_type = 'chat')
+# add_routes(app, agent_executor.with_types(input_type = StrInput, output_type = Output))
+
+
+# Non-agent chain-logic version
+
+add_routes(app, compound_chain.with_types(input_type = StrInput))
+# add_routes(app, compound_chain.with_types(input_type = Input), playground_type = 'chat')
+
+
+
+if __name__ == '__main__':
+    import uvicorn
+
+    uvicorn.run(app, host = 'localhost', port = 8000)
+
+

app_notebook.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -13,7 +13,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -28,7 +28,7 @@
       "\u001b[1;31mHTTPStatusError\u001b[0m: Server error '500 Internal Server Error' for url 'http://localhost:8000/invoke'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/500",
       "\nDuring handling of the above exception, another exception occurred:\n",
       "\u001b[1;31mHTTPStatusError\u001b[0m                           Traceback (most recent call last)",
-      "Cell \u001b[1;32mIn[3], line 2\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;66;03m# remote_runnable.invoke(dict(input = 'Do you know the tragedy of Darth Plagueis the Wise?'))\u001b[39;00m\n\u001b[1;32m----> 2\u001b[0m \u001b[43mremote_runnable\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mDo you know the tragedy of Darth Plagueis the Wise?\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n",
+      "Cell \u001b[1;32mIn[7], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[43mremote_runnable\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mDo you know the tragedy of Darth Plagueis the Wise?\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m      2\u001b[0m \u001b[38;5;66;03m# remote_runnable.invoke(dict(input = 'Do you know the tragedy of Darth Plagueis the Wise?', chat_history = []))\u001b[39;00m\n",
       "File \u001b[1;32mc:\\Users\\Dr-Lo\\miniconda3\\envs\\ML11\\Lib\\site-packages\\langserve\\client.py:356\u001b[0m, in \u001b[0;36mRemoteRunnable.invoke\u001b[1;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[0;32m    354\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m kwargs:\n\u001b[0;32m    355\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mNotImplementedError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mkwargs not implemented yet.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m--> 356\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\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_invoke\u001b[49m\u001b[43m,\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[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[43m)\u001b[49m\n",
       "File \u001b[1;32mc:\\Users\\Dr-Lo\\miniconda3\\envs\\ML11\\Lib\\site-packages\\langchain_core\\runnables\\base.py:1625\u001b[0m, in \u001b[0;36mRunnable._call_with_config\u001b[1;34m(self, func, input, config, run_type, **kwargs)\u001b[0m\n\u001b[0;32m   1621\u001b[0m     context \u001b[38;5;241m=\u001b[39m copy_context()\n\u001b[0;32m   1622\u001b[0m     context\u001b[38;5;241m.\u001b[39mrun(var_child_runnable_config\u001b[38;5;241m.\u001b[39mset, child_config)\n\u001b[0;32m   1623\u001b[0m     output \u001b[38;5;241m=\u001b[39m cast(\n\u001b[0;32m   1624\u001b[0m         Output,\n\u001b[1;32m-> 1625\u001b[0m         \u001b[43mcontext\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1626\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[0;32m   1627\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[0;32m   1628\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[0;32m   1629\u001b[0m \u001b[43m            \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1630\u001b[0m \u001b[43m            \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1631\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[0;32m   1632\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m,\n\u001b[0;32m   1633\u001b[0m     )\n\u001b[0;32m   1634\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[0;32m   1635\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n",
       "File \u001b[1;32mc:\\Users\\Dr-Lo\\miniconda3\\envs\\ML11\\Lib\\site-packages\\langchain_core\\runnables\\config.py:347\u001b[0m, in \u001b[0;36mcall_func_with_variable_args\u001b[1;34m(func, input, config, run_manager, **kwargs)\u001b[0m\n\u001b[0;32m    345\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[0;32m    346\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[1;32m--> 347\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",
@@ -40,8 +40,8 @@
     }
    ],
    "source": [
-    "# remote_runnable.invoke(dict(input = 'Do you know the tragedy of Darth Plagueis the Wise?'))\n",
-    "remote_runnable.invoke('Do you know the tragedy of Darth Plagueis the Wise?')"
+    "remote_runnable.invoke(dict(input = 'Do you know the tragedy of Darth Plagueis the Wise?', chat_history = []))\n",
+    "# remote_runnable.invoke(dict(input = 'What power source did the Death Star use?', chat_history = []))"
    ]
   }
  ],

explore.ipynb

@@ -723,6 +723,27 @@
     "# get_wookieepedia_context('Do you know the Tragedy of Darth Plagueis the Wise?', 'Darth Plagueis', woo_db)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Local embedding model (unsure whether needed for deployment)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from sentence_transformers import SentenceTransformer\n",
+    "\n",
+    "# modelPath = 'embedding_model'\n",
+    "# model = SentenceTransformer('all-MiniLM-L6-v2')\n",
+    "# model.save(modelPath)\n",
+    "# model = SentenceTransformer(modelPath)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

serve.py → ingredients.py

@@ -5,7 +5,7 @@ from langchain_community.document_loaders import DirectoryLoader, TextLoader, We
 # from langchain_chroma import Chroma # The documentation uses this one, but it is extremely recent, and the same functionality is available in langchain_community and langchain (which imports community)
 from langchain_community.vectorstores import Chroma # This has documentation on-hover, while the indirect import through non-community does not
 from langchain_community.embeddings.sentence_transformer import SentenceTransformerEmbeddings # The free alternative (also the default in docs, with model_name = 'all-MiniLM-L6-v2')
-from langchain.text_splitter import RecursiveCharacterTextSplitter#, TextSplitter # Recursive to better keep related bits contiguous (also recommended in docs: https://python.langchain.com/docs/modules/data_connection/document_transformers/)
+from langchain.text_splitter import RecursiveCharacterTextSplitter # Recursive to better keep related bits contiguous (also recommended in docs: https://python.langchain.com/docs/modules/data_connection/document_transformers/)
 
 # Chains
 from langchain.prompts import PromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate, ChatPromptTemplate, MessagesPlaceholder
@@ -24,11 +24,6 @@ from langchain.agents import create_tool_calling_agent, AgentExecutor
 from langchain_core.messages import HumanMessage, AIMessage
 from langchain_core.documents import Document
 
-# To serve the app
-from fastapi import FastAPI
-from langchain_core.messages import BaseMessage
-from langserve import add_routes, CustomUserType
-
 import requests
 from bs4 import BeautifulSoup
 
@@ -40,6 +35,8 @@ import dotenv
 dotenv.load_dotenv()
 
 
+
+
 ## Vector stores
 
 script_db = Chroma(embedding_function = SentenceTransformerEmbeddings(model_name = 'all-MiniLM-L6-v2'), persist_directory = r'scripts\db')
@@ -207,48 +204,3 @@ def compound_retriever(question):
 compound_chain = create_retrieval_chain(compound_retriever, document_chain)
 
 
-
-## Type specifications (with unusual class-scope fields)
-
-class StrInput(BaseModel):
-    input: str
-
-class Input(BaseModel):
-    input: str
-    chat_history: list[BaseMessage] = Field(
-        ...,
-        extra = dict(widget = dict(type = 'chat', input = 'location')),
-    )
-
-class Output(BaseModel):
-    output: str
-
-
-
-## App definition
-
-app = FastAPI(
-  title = 'LangChain Server',
-  version = '1.0',
-  description = 'Simple version of a Star Wars expert',
-)
-
-
-# add_routes(app, script_db.as_retriever())
-# add_routes(app, full_chain.with_types(input_type = StrInput, output_type = Output), playground_type = 'default')
-
-# NOTE: The chat playground type has a web page issue (flashes and becomes white, hence non-interactable; this was supposedly solved in an issue late last year)
-
-# add_routes(app, agent_executor, playground_type = 'chat')
-# add_routes(app, agent_executor.with_types(input_type = StrInput, output_type = Output))
-
-add_routes(app, compound_chain.with_types(input_type = StrInput))
-
-
-
-if __name__ == '__main__':
-    import uvicorn
-
-    uvicorn.run(app, host = 'localhost', port = 8000)
-
-