update env vars & repin toolkit

Signed-off-by: Panos Vagenas <[email protected]>
DS4SD · May 31, 2024 · 84ea7e1 · 84ea7e1
1 parent 861b26b
commit 84ea7e1
Show file tree

Hide file tree

Showing 7 changed files with 79 additions and 102 deletions.
diff --git a/.github/workflows/nb_runner.yml b/.github/workflows/nb_runner.yml
@@ -30,10 +30,9 @@ jobs:
           DEEPSEARCH_VERIFY_SSL: ${{ vars.DEEPSEARCH_VERIFY_SSL }}
           DS_NB_PROJ_KEY: ${{ vars.DS_NB_PROJ_KEY }}
           DS_NR_EXCLUDED: ${{ vars.DS_NR_EXCLUDED }}
-          DS_NB_SEM_ON_IDX_KEY: ${{ vars.DS_NB_SEM_ON_IDX_KEY }}
-          DS_NB_RAISE_ON_SEM_ERR: ${{ vars.DS_NB_RAISE_ON_SEM_ERR }}
-          DS_NB_SEM_ON_IDX_DOC_HASH: ${{ vars.DS_NB_SEM_ON_IDX_DOC_HASH }}
-          DS_NB_SEM_OFF_IDX_KEY: ${{ vars.DS_NB_SEM_OFF_IDX_KEY }}
-          DS_NB_SEM_OFF_IDX_DOC_HASH: ${{ vars.DS_NB_SEM_OFF_IDX_DOC_HASH }}
+          DS_NB_QA_IDX_KEY: ${{ vars.DS_NB_QA_IDX_KEY }}
+          DS_NB_QA_DOC_HASH: ${{ vars.DS_NB_QA_DOC_HASH }}
+          DS_NB_QUESTION: ${{ vars.DS_NB_QUESTION }}
+          DS_NB_GEN_TIMEOUT: ${{ vars.DS_NB_GEN_TIMEOUT }}
           DS_NB_INDEX_KEY: ${{ vars.DS_NB_INDEX_KEY }}
         run: poetry run python -m nbrunner.nb_runner
diff --git a/dsnotebooks/settings.py b/dsnotebooks/settings.py
@@ -1,7 +1,6 @@
 from datetime import datetime
 from typing import Optional
 
-from deepsearch.cps.queries import ConstrainedWeight
 from dotenv import find_dotenv
 from pydantic.v1 import BaseSettings, validator
 
@@ -36,18 +35,3 @@ def set_kg_key(cls, v):
 class CollOptionalNotebookSettings(NotebookSettings):
     proj_key: Optional[str] = None
     index_key: Optional[str] = None
-
-
-class CollQANotebookSettings(ProjectNotebookSettings):
-    sem_on_idx_key: str
-    retr_k: int = 5
-    text_weight: ConstrainedWeight = 0.1
-    rerank: bool = False
-    skip_ingested_docs: bool = True
-    raise_on_sem_err: bool = True
-
-
-class DocQANotebookSettings(CollQANotebookSettings):
-    sem_on_idx_doc_hash: str
-    sem_off_idx_key: str
-    sem_off_idx_doc_hash: str
diff --git a/examples/qa/qa_deep_dive.ipynb b/examples/qa/qa_deep_dive.ipynb
@@ -45,27 +45,22 @@
    "source": [
     "import os\n",
     "from dotenv import load_dotenv\n",
+    "from pydantic import TypeAdapter\n",
     "\n",
     "load_dotenv()\n",
     "\n",
-    "# profile to use (user's active profile will be used by default):\n",
-    "PROFILE_NAME = os.environ.get(\"DS_NB_PROFILE\")\n",
-    "\n",
+    "PROFILE_NAME = os.environ.get(\"DS_NB_PROFILE\")  # profile to use; defaults to active one\n",
     "PROJ_KEY = os.environ[\"DS_NB_PROJ_KEY\"]  # project to use\n",
-    "INDEX_KEY = os.environ[\"DS_NB_SEM_ON_IDX_KEY\"]\n",
-    "\n",
-    "# set the doc hash when targeting a specific document\n",
-    "DOC_HASH = os.environ.get(\"DS_NB_SEM_ON_IDX_DOC_HASH\")\n",
-    "QUESTION = os.environ[\"DS_NB_SEM_ON_QUESTION\"]\n",
-    "\n",
-    "from pydantic import TypeAdapter\n",
+    "INDEX_KEY = os.environ[\"DS_NB_QA_IDX_KEY\"]\n",
+    "DOC_HASH = os.environ.get(\"DS_NB_QA_DOC_HASH\")  # set only when targeting a specific doc\n",
+    "QUESTION = os.environ[\"DS_NB_QUESTION\"]\n",
     "\n",
-    "# whether to skip any already semantically ingested docs:\n",
+    "# whether to ingest incrementally:\n",
     "SKIP_INGESTED_DOCS = TypeAdapter(bool).validate_python(\n",
     "    os.environ.get(\"DS_NB_SKIP_INGESTED_DOCS\", True)\n",
     ")\n",
     "RETR_K = os.environ.get(\"DS_NB_RETR_K\", 3)  # number of search results to retrieve\n",
-    "GEN_TIMEOUT = os.environ.get(\"DB_NB_GEN_TIMEOUT\")  # generation timeout in secs"
+    "GEN_TIMEOUT = os.environ.get(\"DS_NB_GEN_TIMEOUT\", 10)  # generation timeout in seconds"
    ]
   },
   {
@@ -634,16 +629,16 @@
      "data": {
       "text/html": [
        "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #800080; text-decoration-color: #800080; font-weight: bold\">QueryTimings</span><span style=\"font-weight: bold\">(</span>\n",
-       "    <span style=\"color: #808000; text-decoration-color: #808000\">overall</span>=<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.1071437392383814</span>,\n",
+       "    <span style=\"color: #808000; text-decoration-color: #808000\">overall</span>=<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.606383173726499</span>,\n",
        "    <span style=\"color: #808000; text-decoration-color: #808000\">tasks</span>=<span style=\"font-weight: bold\">{</span>\n",
        "        <span style=\"color: #008000; text-decoration-color: #008000\">'QA'</span>: <span style=\"color: #800080; text-decoration-color: #800080; font-weight: bold\">TaskTimings</span><span style=\"font-weight: bold\">(</span>\n",
-       "            <span style=\"color: #808000; text-decoration-color: #808000\">overall</span>=<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.106700461357832</span>,\n",
+       "            <span style=\"color: #808000; text-decoration-color: #808000\">overall</span>=<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.6060180617496371</span>,\n",
        "            <span style=\"color: #808000; text-decoration-color: #808000\">details</span>=<span style=\"font-weight: bold\">{</span>\n",
-       "                <span style=\"color: #008000; text-decoration-color: #008000\">'pipeline'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.7934164367616177</span>,\n",
-       "                <span style=\"color: #008000; text-decoration-color: #008000\">'encode'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.02867589332163334</span>,\n",
-       "                <span style=\"color: #008000; text-decoration-color: #008000\">'search'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.01751641556620598</span>,\n",
+       "                <span style=\"color: #008000; text-decoration-color: #008000\">'pipeline'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.115321146324277</span>,\n",
+       "                <span style=\"color: #008000; text-decoration-color: #008000\">'encode'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.028653355315327644</span>,\n",
+       "                <span style=\"color: #008000; text-decoration-color: #008000\">'search'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.02463858388364315</span>,\n",
        "                <span style=\"color: #008000; text-decoration-color: #008000\">'rerank'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.0</span>,\n",
-       "                <span style=\"color: #008000; text-decoration-color: #008000\">'generate'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.7073831260204315</span>\n",
+       "                <span style=\"color: #008000; text-decoration-color: #008000\">'generate'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.0093672648072243</span>\n",
        "            <span style=\"font-weight: bold\">}</span>\n",
        "        <span style=\"font-weight: bold\">)</span>\n",
        "    <span style=\"font-weight: bold\">}</span>\n",
@@ -652,16 +647,16 @@
       ],
       "text/plain": [
        "\u001b[1;35mQueryTimings\u001b[0m\u001b[1m(\u001b[0m\n",
-       "    \u001b[33moverall\u001b[0m=\u001b[1;36m1\u001b[0m\u001b[1;36m.1071437392383814\u001b[0m,\n",
+       "    \u001b[33moverall\u001b[0m=\u001b[1;36m1\u001b[0m\u001b[1;36m.606383173726499\u001b[0m,\n",
        "    \u001b[33mtasks\u001b[0m=\u001b[1m{\u001b[0m\n",
        "        \u001b[32m'QA'\u001b[0m: \u001b[1;35mTaskTimings\u001b[0m\u001b[1m(\u001b[0m\n",
-       "            \u001b[33moverall\u001b[0m=\u001b[1;36m1\u001b[0m\u001b[1;36m.106700461357832\u001b[0m,\n",
+       "            \u001b[33moverall\u001b[0m=\u001b[1;36m1\u001b[0m\u001b[1;36m.6060180617496371\u001b[0m,\n",
        "            \u001b[33mdetails\u001b[0m=\u001b[1m{\u001b[0m\n",
-       "                \u001b[32m'pipeline'\u001b[0m: \u001b[1;36m0.7934164367616177\u001b[0m,\n",
-       "                \u001b[32m'encode'\u001b[0m: \u001b[1;36m0.02867589332163334\u001b[0m,\n",
-       "                \u001b[32m'search'\u001b[0m: \u001b[1;36m0.01751641556620598\u001b[0m,\n",
+       "                \u001b[32m'pipeline'\u001b[0m: \u001b[1;36m1.115321146324277\u001b[0m,\n",
+       "                \u001b[32m'encode'\u001b[0m: \u001b[1;36m0.028653355315327644\u001b[0m,\n",
+       "                \u001b[32m'search'\u001b[0m: \u001b[1;36m0.02463858388364315\u001b[0m,\n",
        "                \u001b[32m'rerank'\u001b[0m: \u001b[1;36m0.0\u001b[0m,\n",
-       "                \u001b[32m'generate'\u001b[0m: \u001b[1;36m0.7073831260204315\u001b[0m\n",
+       "                \u001b[32m'generate'\u001b[0m: \u001b[1;36m1.0093672648072243\u001b[0m\n",
        "            \u001b[1m}\u001b[0m\n",
        "        \u001b[1m)\u001b[0m\n",
        "    \u001b[1m}\u001b[0m\n",
@@ -861,15 +856,15 @@
      "data": {
       "text/html": [
        "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #800080; text-decoration-color: #800080; font-weight: bold\">QueryTimings</span><span style=\"font-weight: bold\">(</span>\n",
-       "    <span style=\"color: #808000; text-decoration-color: #808000\">overall</span>=<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.1048420211300254</span>,\n",
+       "    <span style=\"color: #808000; text-decoration-color: #808000\">overall</span>=<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.1053222483024001</span>,\n",
        "    <span style=\"color: #808000; text-decoration-color: #808000\">tasks</span>=<span style=\"font-weight: bold\">{</span>\n",
        "        <span style=\"color: #008000; text-decoration-color: #008000\">'QA'</span>: <span style=\"color: #800080; text-decoration-color: #800080; font-weight: bold\">TaskTimings</span><span style=\"font-weight: bold\">(</span>\n",
-       "            <span style=\"color: #808000; text-decoration-color: #808000\">overall</span>=<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.1045362269505858</span>,\n",
+       "            <span style=\"color: #808000; text-decoration-color: #808000\">overall</span>=<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.1050042947754264</span>,\n",
        "            <span style=\"color: #808000; text-decoration-color: #808000\">details</span>=<span style=\"font-weight: bold\">{</span>\n",
-       "                <span style=\"color: #008000; text-decoration-color: #008000\">'pipeline'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.6429227869957685</span>,\n",
-       "                <span style=\"color: #008000; text-decoration-color: #008000\">'encode'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.0342963021248579</span>,\n",
-       "                <span style=\"color: #008000; text-decoration-color: #008000\">'search'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.026565583422780037</span>,\n",
-       "                <span style=\"color: #008000; text-decoration-color: #008000\">'rerank'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.5808815937489271</span>\n",
+       "                <span style=\"color: #008000; text-decoration-color: #008000\">'pipeline'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.6090765688568354</span>,\n",
+       "                <span style=\"color: #008000; text-decoration-color: #008000\">'encode'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.026338623836636543</span>,\n",
+       "                <span style=\"color: #008000; text-decoration-color: #008000\">'search'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.025418167933821678</span>,\n",
+       "                <span style=\"color: #008000; text-decoration-color: #008000\">'rerank'</span>: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">0.5562568940222263</span>\n",
        "            <span style=\"font-weight: bold\">}</span>\n",
        "        <span style=\"font-weight: bold\">)</span>\n",
        "    <span style=\"font-weight: bold\">}</span>\n",
@@ -878,15 +873,15 @@
       ],
       "text/plain": [
        "\u001b[1;35mQueryTimings\u001b[0m\u001b[1m(\u001b[0m\n",
-       "    \u001b[33moverall\u001b[0m=\u001b[1;36m1\u001b[0m\u001b[1;36m.1048420211300254\u001b[0m,\n",
+       "    \u001b[33moverall\u001b[0m=\u001b[1;36m1\u001b[0m\u001b[1;36m.1053222483024001\u001b[0m,\n",
        "    \u001b[33mtasks\u001b[0m=\u001b[1m{\u001b[0m\n",
        "        \u001b[32m'QA'\u001b[0m: \u001b[1;35mTaskTimings\u001b[0m\u001b[1m(\u001b[0m\n",
-       "            \u001b[33moverall\u001b[0m=\u001b[1;36m1\u001b[0m\u001b[1;36m.1045362269505858\u001b[0m,\n",
+       "            \u001b[33moverall\u001b[0m=\u001b[1;36m1\u001b[0m\u001b[1;36m.1050042947754264\u001b[0m,\n",
        "            \u001b[33mdetails\u001b[0m=\u001b[1m{\u001b[0m\n",
-       "                \u001b[32m'pipeline'\u001b[0m: \u001b[1;36m0.6429227869957685\u001b[0m,\n",
-       "                \u001b[32m'encode'\u001b[0m: \u001b[1;36m0.0342963021248579\u001b[0m,\n",
-       "                \u001b[32m'search'\u001b[0m: \u001b[1;36m0.026565583422780037\u001b[0m,\n",
-       "                \u001b[32m'rerank'\u001b[0m: \u001b[1;36m0.5808815937489271\u001b[0m\n",
+       "                \u001b[32m'pipeline'\u001b[0m: \u001b[1;36m0.6090765688568354\u001b[0m,\n",
+       "                \u001b[32m'encode'\u001b[0m: \u001b[1;36m0.026338623836636543\u001b[0m,\n",
+       "                \u001b[32m'search'\u001b[0m: \u001b[1;36m0.025418167933821678\u001b[0m,\n",
+       "                \u001b[32m'rerank'\u001b[0m: \u001b[1;36m0.5562568940222263\u001b[0m\n",
        "            \u001b[1m}\u001b[0m\n",
        "        \u001b[1m)\u001b[0m\n",
        "    \u001b[1m}\u001b[0m\n",

diff --git a/examples/qa/qa_quick_start.ipynb b/examples/qa/qa_quick_start.ipynb
@@ -38,34 +38,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 1,
    "id": "5b244bdd-1b52-41ff-b63e-9a203570d210",
    "metadata": {},
    "outputs": [],
    "source": [
     "import os\n",
     "from dotenv import load_dotenv\n",
+    "from pydantic import TypeAdapter\n",
     "\n",
     "load_dotenv()\n",
     "\n",
-    "# profile to use (user's active profile will be used by default):\n",
-    "PROFILE_NAME = os.environ.get(\"DS_NB_PROFILE\")\n",
-    "\n",
+    "PROFILE_NAME = os.environ.get(\"DS_NB_PROFILE\")  # profile to use; defaults to active one\n",
     "PROJ_KEY = os.environ[\"DS_NB_PROJ_KEY\"]  # project to use\n",
-    "INDEX_KEY = os.environ[\"DS_NB_SEM_ON_IDX_KEY\"]\n",
+    "INDEX_KEY = os.environ[\"DS_NB_QA_IDX_KEY\"]\n",
+    "DOC_HASH = os.environ.get(\"DS_NB_QA_DOC_HASH\")  # set only when targeting a specific doc\n",
+    "QUESTION = os.environ[\"DS_NB_QUESTION\"]\n",
     "\n",
-    "# set the doc hash when targeting a specific document\n",
-    "DOC_HASH = os.environ.get(\"DS_NB_SEM_ON_IDX_DOC_HASH\")\n",
-    "QUESTION = os.environ[\"DS_NB_SEM_ON_QUESTION\"]\n",
-    "\n",
-    "from pydantic import TypeAdapter\n",
-    "\n",
-    "# whether to skip any already semantically ingested docs:\n",
+    "# whether to ingest incrementally:\n",
     "SKIP_INGESTED_DOCS = TypeAdapter(bool).validate_python(\n",
     "    os.environ.get(\"DS_NB_SKIP_INGESTED_DOCS\", True)\n",
     ")\n",
     "RETR_K = os.environ.get(\"DS_NB_RETR_K\", 3)  # number of search results to retrieve\n",
-    "GEN_TIMEOUT = os.environ.get(\"DB_NB_GEN_TIMEOUT\")  # generation timeout in secs"
+    "GEN_TIMEOUT = os.environ.get(\"DS_NB_GEN_TIMEOUT\", 10)  # generation timeout in seconds"
    ]
   },
   {
@@ -78,7 +73,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 2,
    "id": "5d236ea0-db1c-4171-8e11-cdd0bad69d66",
    "metadata": {},
    "outputs": [],
@@ -100,7 +95,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 3,
    "id": "9c108432-a285-4c7b-a996-008ac3ff3d7a",
    "metadata": {},
    "outputs": [],
@@ -122,7 +117,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 4,
    "id": "adc0f7a4",
    "metadata": {},
    "outputs": [],
@@ -150,17 +145,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 5,
    "id": "947e87c5",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/pva/work/github.com/DS4SD/deepsearch-examples/.venv/lib/python3.10/site-packages/pydantic/main.py:347: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `_LiteralGenericAlias` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
        "{'ing_out': {}}"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -190,7 +194,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 6,
    "id": "b960b309",
    "metadata": {},
    "outputs": [
@@ -403,7 +407,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 7,
    "id": "492fd066",
    "metadata": {},
    "outputs": [

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -11,7 +11,7 @@ packages = [
 
 [tool.poetry.dependencies]
 python = ">= 3.8, <3.11"
-deepsearch-toolkit = { git = "https://github.com/DS4SD/deepsearch-toolkit.git", rev = "e27a294322ebee27645afb3bffa57052d4677941" }
+deepsearch-toolkit = "^0.46.0"
 jupyter = "^1.0.0"
 ipywidgets = "^7"  # previous major release is needed bcause of mols2grid
 numpy = "^1.23.4"