Updates

1 files changed, 24 insertions, 34 deletions

diff --git a/notebooks/testing.ipynb b/notebooks/testing.ipynb
index 2bd3dd6..36dd3af 100644
--- a/notebooks/testing.ipynb
+++ b/notebooks/testing.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "c1f56ae3-a056-4b31-bcab-27c2c97c00f1",
    "metadata": {},
    "outputs": [],
@@ -18,7 +18,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "6b5cb12e-df7e-4532-b78b-216e11ed6161",
    "metadata": {},
    "outputs": [],
@@ -28,7 +28,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "b8382795-9610-4b24-80b7-31397b2faf90",
    "metadata": {},
    "outputs": [
@@ -36,8 +36,8 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[32m2024-04-06 01:37:11.913\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mrag.db.document\u001b[0m:\u001b[36m__configure\u001b[0m:\u001b[36m26\u001b[0m - \u001b[34m\u001b[1mCreating documents table if it does not exist...\u001b[0m\n",
-      "\u001b[32m2024-04-06 01:37:11.926\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mrag.db.vector\u001b[0m:\u001b[36m__configure\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCollection knowledge-base already exists...\u001b[0m\n"
+      "\u001b[32m2024-04-07 21:14:48.364\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mrag.db.vector\u001b[0m:\u001b[36m__configure\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCollection knowledge-base already exists...\u001b[0m\n",
+      "\u001b[32m2024-04-07 21:14:48.368\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mrag.db.document\u001b[0m:\u001b[36m__configure\u001b[0m:\u001b[36m25\u001b[0m - \u001b[34m\u001b[1mCreating documents table if it does not exist...\u001b[0m\n"
      ]
     }
    ],
@@ -47,27 +47,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "ac57e50d-1fc3-4fc9-90e5-5bdb97bd2f5e",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2024-04-06 01:37:17.243\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mrag.db.document\u001b[0m:\u001b[36madd_document\u001b[0m:\u001b[36m37\u001b[0m - \u001b[34m\u001b[1mInserting document hash into documents db...\u001b[0m\n",
-      "\u001b[32m2024-04-06 01:37:17.244\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mrag.db.document\u001b[0m:\u001b[36m__hash\u001b[0m:\u001b[36m32\u001b[0m - \u001b[34m\u001b[1mGenerating sha256 hash for pdf document\u001b[0m\n",
-      "\u001b[32m2024-04-06 01:37:17.247\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mrag.rag\u001b[0m:\u001b[36madd_pdf\u001b[0m:\u001b[36m31\u001b[0m - \u001b[34m\u001b[1mDocument already exists!\u001b[0m\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "rag.add_pdf(path)"
+    "rag.add_pdf(path)\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "1c6b48d2-eb04-4a7c-8224-78aabfc7c887",
    "metadata": {},
    "outputs": [],
@@ -77,39 +67,39 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "a95c8250-00b2-4cbc-a9c6-a76d14ef2da5",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "rag.rag(query, \"quant researcher\", limit=5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "2c28db8c-c2bb-4092-b1d3-fd3f8bb060b5",
+   "metadata": {},
    "outputs": [
     {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2024-04-06 01:37:17.265\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mrag.llm.encoder\u001b[0m:\u001b[36mencode_query\u001b[0m:\u001b[36m33\u001b[0m - \u001b[34m\u001b[1mEncoding query: What is a factor model?\u001b[0m\n",
-      "\u001b[32m2024-04-06 01:37:17.858\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mrag.db.vector\u001b[0m:\u001b[36msearch\u001b[0m:\u001b[36m51\u001b[0m - \u001b[34m\u001b[1mSearching for vectors...\u001b[0m\n",
-      "\u001b[32m2024-04-06 01:37:17.864\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mrag.rag\u001b[0m:\u001b[36m__context\u001b[0m:\u001b[36m35\u001b[0m - \u001b[34m\u001b[1mGot 5 hits in the vector db with limit=5\u001b[0m\n",
-      "\u001b[32m2024-04-06 01:37:17.865\u001b[0m | \u001b[34m\u001b[1mDEBUG   \u001b[0m | \u001b[36mrag.llm.generator\u001b[0m:\u001b[36mgenerate\u001b[0m:\u001b[36m32\u001b[0m - \u001b[34m\u001b[1mGenerating answer...\u001b[0m\n"
-     ]
-    },
-    {
      "data": {
       "text/plain": [
-       "'A factor model is a type of model used to explain the returns or movements of financial assets by decomposing them into two parts: systematic risk, which is driven by a small number of factors affecting many securities; and idiosyncratic risk, which is specific to individual stocks. The general factor model is rt = φ0 + h(ft) + wt, where rt denotes the return of an asset at time t, φ0 represents a constant vector, ft is a vector of factors responsible for most of the randomness in the market, and h is a function that summarizes how these low-dimensional factors affect higher-dimensional markets. The residual wt accounts for any remaining uncorrelated perturbations with only a marginal effect on returns.'"
+       "True"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "rag.rag(query, \"quant researcher\", limit=5)"
+    "rag.vector_db.client.delete_collection(\"knowledge-base\")"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "11ac0d46-8589-4700-abf7-7959afbf611c",
+   "id": "05f7068c-b4c6-47b2-ac62-79c021838500",
    "metadata": {},
    "outputs": [],
    "source": []