add new quickstarts to nav (#574)

* add new quickstarts to nav * rename t2t quickstart in nav * text2text format nits, hf colab button * fix extra stuff in vector store specification
truera · Nov 20, 2023 · df3399e · df3399e
1 parent a82bce6
commit df3399e
Show file tree

Hide file tree

Showing 4 changed files with 23 additions and 34 deletions.
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -85,9 +85,12 @@ nav:
       - Getting Started:
           - 🚀 Installation: trulens_eval/install.md
           - ⚡ Quickstarts:
+              - Quickstart: trulens_eval/quickstart.ipynb
               - LangChain Quickstart: trulens_eval/langchain_quickstart.ipynb
               - Llama-Index Quickstart: trulens_eval/llama_index_quickstart.ipynb
-              - Python Native (Text to Text) Quickstart: trulens_eval/text2text_quickstart.ipynb
+              - Text to Text Quickstart: trulens_eval/text2text_quickstart.ipynb
+              - Ground Truth Evaluation Quickstart: trulens_eval/groundtruth_evals.ipynb
+              - Human Feedback Quickstart: trulens_eval/human_feedback.ipynb
           - 🧠 Core Concepts:
               - Feedback Functions: trulens_eval/core_concepts_feedback_functions.md
               - RAG Triad: trulens_eval/core_concepts_rag_triad.md

diff --git a/trulens_eval/examples/quickstart/human_feedback.ipynb b/trulens_eval/examples/quickstart/human_feedback.ipynb
@@ -6,7 +6,9 @@
    "source": [
     "## Logging Human Feedback\n",
     "\n",
-    "In many situations, it can be useful to log human feedback from your users about your LLM app's performance. Combining human feedback along with automated feedback can help you drill down on subsets of your app that underperform, and uncover new failure modes. This example will walk you through a simple example of recording human feedback with TruLens."
+    "In many situations, it can be useful to log human feedback from your users about your LLM app's performance. Combining human feedback along with automated feedback can help you drill down on subsets of your app that underperform, and uncover new failure modes. This example will walk you through a simple example of recording human feedback with TruLens.\n",
+    "\n",
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/truera/trulens/blob/main/trulens_eval/examples/quickstart/human_feedback.ipynb)"
    ]
   },
   {

diff --git a/trulens_eval/examples/quickstart/quickstart.ipynb b/trulens_eval/examples/quickstart/quickstart.ipynb
@@ -73,8 +73,8 @@
     "vector_store.add(\n",
     "    embeddings = students_embeddings,\n",
     "    documents = [university_info],\n",
-    "    metadatas = [{\"source\": \"student info\"},{\"source\": \"club info\"},{'source':'university info'}],\n",
-    "    ids = [\"id1\", \"id2\", \"id3\"]\n",
+    "    metadatas = [{'source':'university info'}],\n",
+    "    ids = [\"id1\"]\n",
     ")"
    ]
   },
@@ -87,6 +87,15 @@
     "Build a custom RAG from scratch, and add TruLens custom instrumentation."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tru.reset_database()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

diff --git a/trulens_eval/examples/quickstart/text2text_quickstart.ipynb b/trulens_eval/examples/quickstart/text2text_quickstart.ipynb
@@ -12,32 +12,14 @@
     "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/truera/trulens/blob/main/trulens_eval/examples/quickstart/text2text_quickstart.ipynb)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# ! pip install trulens_eval==0.17.0 openai==1.1.1"
-   ]
-  },
   {
    "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "## Setup\n",
     "### Add API keys\n",
-    "For this quickstart you will need Open AI and Huggingface keys"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import logging"
+    "For this quickstart you will need an OpenAI Key."
    ]
   },
   {
@@ -50,17 +32,6 @@
     "os.environ[\"OPENAI_API_KEY\"] = \"...\""
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from openai import OpenAI\n",
-    "\n",
-    "client = OpenAI()"
-   ]
-  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -77,6 +48,10 @@
    "source": [
     "from IPython.display import JSON\n",
     "\n",
+    "# Create openai client\n",
+    "from openai import OpenAI\n",
+    "client = OpenAI()\n",
+    "\n",
     "# Imports main tools:\n",
     "from trulens_eval import Feedback, OpenAI as fOpenAI, Tru\n",
     "tru = Tru()\n",