From 9be6762f4747c31c7c7c49322308ab394b668449 Mon Sep 17 00:00:00 2001
From: James Briggs <35938317+jamescalam@users.noreply.github.com>
Date: Mon, 5 Feb 2024 22:51:45 +0100
Subject: [PATCH] updated example
---
.../conversation-topic-splitter.ipynb} | 71 ++++++-------------
1 file changed, 23 insertions(+), 48 deletions(-)
rename docs/{07-route-conversations-by-topic.ipynb => examples/conversation-topic-splitter.ipynb} (76%)
diff --git a/docs/07-route-conversations-by-topic.ipynb b/docs/examples/conversation-topic-splitter.ipynb
similarity index 76%
rename from docs/07-route-conversations-by-topic.ipynb
rename to docs/examples/conversation-topic-splitter.ipynb
index 9d2b5424..5ac130b0 100644
--- a/docs/07-route-conversations-by-topic.ipynb
+++ b/docs/examples/conversation-topic-splitter.ipynb
@@ -18,11 +18,6 @@
"Additionally, splitters have been integrated with `Conversation` objects allowing conversations to be progressively spit by topic as they evolve. This is beneficial to routing, as earlier messages in a conversation topic might provide useful context when determining routes. By using all utterances in the latest conversation this additional context allows for correct routes to be more reliably chosen."
]
},
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": []
- },
{
"cell_type": "markdown",
"metadata": {},
@@ -53,7 +48,7 @@
"name": "stderr",
"output_type": "stream",
"text": [
- "c:\\Users\\Siraj\\Documents\\Personal\\Work\\Aurelio\\20240130 2148 Semantic Topic Splitter (Siraj Local Repo)\\venvs\\semantic_splitter_1\\Lib\\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",
+ "/Users/jamesbriggs/opt/anaconda3/envs/decision-layer/lib/python3.11/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"
]
}
@@ -74,7 +69,7 @@
" Message(\n",
" role=\"bot\", content=\"Okay, is our software running when the computer crashes.\"\n",
" ),\n",
- " Message(role=\"user\", content=\"Yeah, v.3.11.2 is running when it crashes.\"),\n",
+ " Message(role=\"user\", content=\"Yeah, v.3.11.2.\"),\n",
"]\n",
"\n",
"# Add messages to the conversation\n",
@@ -90,24 +85,15 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
- "from semantic_router.encoders.cohere import CohereEncoder\n",
+ "from semantic_router.encoders.openai import OpenAIEncoder\n",
"\n",
- "cohere_encoder = CohereEncoder(\n",
- " name=\"embed-english-v3.0\",\n",
- " cohere_api_key=\"\",\n",
- " input_type=\"search_document\",\n",
- ")"
+ "encoder = OpenAIEncoder(openai_api_key=\"sk-...\")"
]
},
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": []
- },
{
"cell_type": "markdown",
"metadata": {},
@@ -117,26 +103,25 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "No unclustered messages to process.\n",
"\u001b[31muser: Hi, there, please can you confirm your full name\u001b[0m\n",
"\u001b[31muser: Hi, my name is John Doe.\u001b[0m\n",
- "\u001b[32mbot: Okay, how can I help you today?\u001b[0m\n",
- "\u001b[33muser: My computer keeps crashing\u001b[0m\n",
- "\u001b[33mbot: Okay, is our software running when the computer crashes.\u001b[0m\n",
- "\u001b[33muser: Yeah, v.3.11.2 is running when it crashes.\u001b[0m\n"
+ "\u001b[31mbot: Okay, how can I help you today?\u001b[0m\n",
+ "\u001b[32muser: My computer keeps crashing\u001b[0m\n",
+ "\u001b[32mbot: Okay, is our software running when the computer crashes.\u001b[0m\n",
+ "\u001b[32muser: Yeah, v.3.11.2.\u001b[0m\n"
]
}
],
"source": [
"conversation.configure_splitter(\n",
- " encoder=cohere_encoder, threshold=0.5, split_method=\"cumulative_similarity\"\n",
+ " encoder=encoder, threshold=0.78, split_method=\"cumulative_similarity\"\n",
")\n",
"\n",
"all_topics, new_topics = conversation.split_by_topic()\n",
@@ -185,7 +170,7 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
@@ -204,7 +189,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 5,
"metadata": {},
"outputs": [
{
@@ -213,22 +198,22 @@
"text": [
"\u001b[31muser: Hi, there, please can you confirm your full name\u001b[0m\n",
"\u001b[31muser: Hi, my name is John Doe.\u001b[0m\n",
- "\u001b[32mbot: Okay, how can I help you today?\u001b[0m\n",
- "\u001b[33muser: My computer keeps crashing\u001b[0m\n",
- "\u001b[33mbot: Okay, is our software running when the computer crashes.\u001b[0m\n",
- "\u001b[33muser: Yeah, v.3.11.2 is running when it crashes.\u001b[0m\n",
- "\u001b[33muser: What do the system logs say, right before the crash?\u001b[0m\n",
- "\u001b[34muser: I'll check soon, but first let's talk refund.\u001b[0m\n",
- "\u001b[34mbot: Okay let me sort out a refund.\u001b[0m\n"
+ "\u001b[31mbot: Okay, how can I help you today?\u001b[0m\n",
+ "\u001b[32muser: My computer keeps crashing\u001b[0m\n",
+ "\u001b[32mbot: Okay, is our software running when the computer crashes.\u001b[0m\n",
+ "\u001b[32muser: Yeah, v.3.11.2.\u001b[0m\n",
+ "\u001b[32muser: What do the system logs say, right before the crash?\u001b[0m\n",
+ "\u001b[33muser: I'll check soon, but first let's talk refund.\u001b[0m\n",
+ "\u001b[33mbot: Okay let me sort out a refund.\u001b[0m\n"
]
}
],
"source": [
"conversation.configure_splitter(\n",
- " encoder=cohere_encoder, threshold=0.5, split_method=\"cumulative_similarity\"\n",
+ " encoder=encoder, threshold=0.78, split_method=\"cumulative_similarity\"\n",
")\n",
"\n",
- "all_topics, new_topics = conversation.split_by_topic()\n",
+ "all_topics, new_topics = conversation.split_by_topic(force=True)\n",
"\n",
"print(conversation)"
]
@@ -246,16 +231,6 @@
"\n",
"Despite \"user: Yeah, v.3.11.2 is running when it crashes\" and \"user: What do the system logs say, right before the crash?\" being added and separately, and despite the conversation splitter being run twice (once before user: What do the system logs say, right before the crash?\" was added, and once after), both these utterances were successfully assigned the same Topic - `Topic 4`.\n"
]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": []
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": []
}
],
"metadata": {
@@ -274,7 +249,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.11.4"
+ "version": "3.11.5"
}
},
"nbformat": 4,
--
GitLab