# Prompt Engineering and LLMs with Langchain

**URL:** <https://community.pinecone.io/t/prompt-engineering-and-llms-with-langchain/629>\
**Category:** General\
**Created:** [February 13, 2023, 10:30am UTC](https://community.pinecone.io/t/prompt-engineering-and-llms-with-langchain/629 "2023-02-13T10:30:28Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![discobot](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/discobot/32/2_2.png) [@discobot](https://community.pinecone.io/u/discobot)\
**Post date:** [February 13, 2023, 10:30am UTC](https://community.pinecone.io/t/prompt-engineering-and-llms-with-langchain/629/1 "2023-02-13T10:30:28Z")

</div>

We have always relied on different models for different tasks in machine learning. With the introduction of [multi-modality](https://www.pinecone.io/learn/clip/) and Large Language Models (LLMs), this has changed.

Gone are the days when we needed separate models for classification, named entity recognition (NER), question-answering (QA), and many other tasks.

* * *
This is a companion discussion topic for the original entry at [https://www.pinecone.io/learn/langchain-prompt-templates](https://www.pinecone.io/learn/langchain-prompt-templates)

---

<div class="post-metadata">

**Author:** ![dukemagus](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/dukemagus/32/895_2.png) [@dukemagus](https://community.pinecone.io/u/dukemagus)\
**Post date:** [June 27, 2023, 4:59pm UTC](https://community.pinecone.io/t/prompt-engineering-and-llms-with-langchain/629/2 "2023-06-27T16:59:55Z")

</div>

A point that wasn’t discussed in the chapter is the token consumption of prompt templates. Is there a way of making the templates less token consuming without losing accuracy (other than rephrasing the template)?