Cleaned up getting started tutorial and added framework integration links

Author: avthars

README.md

@@ -18,6 +18,12 @@ PostgreSQL++ for AI Applications.
   more](https://www.timescale.com/blog/how-we-made-postgresql-the-best-vector-database/?utm_campaign=vectorlaunch&utm_source=github&utm_medium=direct):
   Learn more about Timescale Vector, how it works and why we built it.
 
+If you prefer to use an LLM development or data framework, see Timescale
+Vector’s integrations with
+[LangChain](https://python.langchain.com/docs/integrations/vectorstores/timescalevector)
+and
+[LlamaIndex](https://gpt-index.readthedocs.io/en/stable/examples/vector_stores/Timescalevector.html)
+
 ## Install
 
 ``` sh

nbs/index.ipynb

@@ -18,7 +18,10 @@
     "- [Signup for Timescale Vector](https://console.cloud.timescale.com/signup?utm_campaign=vectorlaunch&utm_source=github&utm_medium=direct): Get 90 days free to try Timescale Vector on the Timescale cloud data platform. There is no self-managed version at this time.\n",
     "- [Documentation](https://timescale.github.io/python-vector/): Learn the key features of Timescale Vector and how to use them.\n",
     "- [Getting Started Tutorial](https://timescale.github.io/python-vector/tsv_python_getting_started_tutorial.html): Learn how to use Timescale Vector for semantic search on a real world dataset.\n",
-    "- [Learn more](https://www.timescale.com/blog/how-we-made-postgresql-the-best-vector-database/?utm_campaign=vectorlaunch&utm_source=github&utm_medium=direct): Learn more about Timescale Vector, how it works and why we built it."
+    "- [Learn more](https://www.timescale.com/blog/how-we-made-postgresql-the-best-vector-database/?utm_campaign=vectorlaunch&utm_source=github&utm_medium=direct): Learn more about Timescale Vector, how it works and why we built it.\n",
+    "\n",
+    "\n",
+    "If you prefer to use an LLM development or data framework, see Timescale Vector's integrations with [LangChain](https://python.langchain.com/docs/integrations/vectorstores/timescalevector) and [LlamaIndex](https://gpt-index.readthedocs.io/en/stable/examples/vector_stores/Timescalevector.html)"
    ]
   },
   {

nbs/tsv_python_getting_started_tutorial.ipynb

@@ -432,9 +432,7 @@
     "\n",
     "We'll define a helper funciton `create_uuid()` to create a uuid for commit message and associated vector embedding based on its timestamp. \n",
     "\n",
-    "In the helper function, we'll use the timescale vector client library's `uuid_from_time()` method to take a date and create a uuid with a datetime portion that reflects the date string.\n",
-    "\n",
-    "Important note: If you are working with documents/nodes and want the current date and time associated with vector for time-based search, you can skip this step. A uuid will be automatically generated when the nodes are added to the table in Timescale Vector by default. In our case, because we want the uuid to be based on the timestamp in the past, we need to create the uuids manually."
+    "In the helper function, we'll use the timescale vector client library's `uuid_from_time()` method to take a date and create a uuid with a datetime portion that reflects the date string."
    ]
   },
   {
@@ -974,7 +972,7 @@
     "\n",
     "- The first step to using time filtering with Timescale Vector is to create a table with the `time_partition_interval` argument set to the desired time interval. This will automatically partition the table into time-based chunks to speed up queries. We completed this step in Part 1 above.\n",
     "\n",
-    "- Next, we ensure the `id` of our row is a `uuid` with a datetime portion that reflects the date and time we want to associated with the embedding. We completed this step in Part 2 above.\n",
+    "- Next, we ensure the `id` of our row is a `uuid` with a datetime portion that reflects the date and time we want to associated with the embedding. We completed this step in Part 2 above, where we used the `uuid_from_time()` method provided by the Timescale Vector library.\n",
     "\n",
     "- Finally, we can run similarity searches with time range filters using the TimescaleVector client. We'll illustrate this below."
    ]