Merge branch 'trigaten:main' into main

(docs)/ar/docs/additional/page.mdx

@@ -0,0 +1,77 @@
+export const metadata = {
+  sidebar_position: 3000,
+  title: "🛸 Additional Resources",
+};
+
+# 🛸 Additional Resources
+
+## Interactive Tutorials
+
+- [agents.blue](https://www.agents.blue/) - A free, guided tutorial on prompt engineering.
+
+## Resources
+
+- [Article on leaking Notion's prompts](https://lspace.swyx.io/p/reverse-prompt-eng)
+- [A great article on applications](https://huyenchip.com/2023/04/11/llm-engineering.html)
+  <br />
+- [A fantastic PE intro video](https://youtube.com/watch?v=dOxUroR57xs&feature=shares)
+  <br />
+- [A very nice, short prompt engineering guide](https://help.openai.com/en/articles/6654000-best-practices-for-prompt-engineering-with-openai-api)
+  <br />
+- [A great prompt engineering intro](https://humanloop.com/blog/prompt-engineering-101)
+  <br />
+- [A nice collection of prompt engineering papers](https://github.com/dair-ai/Prompt-Engineering-Guide)
+  <br />
+- [Many more prompt engineering papers](https://github.com/thunlp/PromptPapers)
+  <br />
+- [CMU class on prompt engineering](https://youtu.be/5ef83Wljm-M)
+  <br />
+- [How Copilot works](https://thakkarparth007.github.io/copilot-explorer/posts/copilot-internals.html)
+  <br />
+- [A Beginners Guide to Prompt Writing by Zapier](https://zapier.com/blog/gpt-3-prompt/)
+  <br />
+- [Awesome A-Z Prompt-Engineering Resources list](https://github.com/promptslab/Awesome-Prompt-Engineering)
+  <br />
+- [500 ChatGPT prompt templates](https://www.notion.so/500-ChatGPT-Prompt-Templates-d9541e901b2b4e8f800e819bdc0256da)
+  <br />
+- [Prompt base](https://promptbase.com/)
+  <br />
+- [Prompt vibes](https://www.promptvibes.com/)
+  <br />
+- [Prompt Hero](https://prompthero.com/)
+- [Midjourney community showcase with prompts](https://www.midjourney.com/showcase/recent/)
+  <br />
+- [Data Science Prompts](https://github.com/travistangvh/ChatGPT-Data-Science-Prompts.git)
+- [ALL styles and references for midjourney](https://github.com/willwulfken/MidJourney-Styles-and-Keywords-Reference)
+  <br />
+- [Advanced Prompt Engineering](https://jamesbachini.com/advanced-midjourney-prompt-engineering/#midjourney-flags)
+- [Ordinary people prompts](https://www.ordinarypeopleprompts.com/)
+
+### GPT-3 Prompt Examples/Ideas
+
+https://sharegpt.com<br />
+https://www.learngpt.com<br />
+https://chatgpt.getlaunchlist.com<br />
+https://prompts.chat
+
+## Facts
+
+GPT-3 is _NOT_ deterministic: https://twitter.com/BorisMPower/status/1608522707372740609
+
+## People to follow
+
+I source significant content from these people.
+
+[@chillzaza\_](https://mobile.twitter.com/chillzaza_) Prompt engineering, tools, toolbot<br />
+[@mathemagic1an](https://mobile.twitter.com/mathemagic1an) Various prompting, PE,
+GPT3 info<br />
+[@goodside](https://twitter.com/goodside/status/1588247865503010816) Prompt Injection,
+PE tooling<br />
+[@hwchase17](https://twitter.com/hwchase17) Core dev of langchain<br />
+[@omarsar0](https://twitter.com/omarsar0) DAIR AI lead
+
+Also check accounts that I follow: https://twitter.com/learnprompting/following
+
+## Even More
+
+Check [open issues](https://github.com/trigaten/Learn_Prompting/issues) and [PRs](https://github.com/trigaten/Learn_Prompting/pulls) :)

(docs)/ar/docs/advanced_applications/_category_.json

@@ -0,0 +1 @@
+{"label":"🚀 المستوى المتقدم","position":20,"link":{"type":"generated-index","description":"بعض التطبيقات القوية جدًا ، ولكنها أكثر تقدمًا للهندسة الذكاء الاصطناعي."}}

(docs)/ar/docs/advanced_applications/mrkl/page.mdx

@@ -0,0 +1,152 @@
+export const metadata = { sidebar_position: 2, title: "🟡 LLMs Using Tools" };
+
+# 🟡 LLMs Using Tools
+
+MRKL Systems(@karpas2022mrkl) (Modular Reasoning, Knowledge and Language, pronounced "miracle")
+are a **neuro-symbolic architecture** that combine LLMs (neural computation) and external
+tools like calculators (symbolic computation), to solve complex problems.
+
+A MRKL system is composed of a set of modules (e.g. a calculator, weather API, database, etc.) and a router that decides how to 'route' incoming natural language queries to the appropriate module.
+
+A simple example of a MRKL system is a LLM that can
+use a calculator app. This is a single module system, where the LLM is the router.
+When asked, `What is 100*100?`, the LLM can choose to
+extract the numbers from the prompt, and then tell the MRKL System to use a calculator
+app to compute the result. This might look like the following:
+
+<pre>
+  <p>What is 100*100?</p>
+
+  <span className="bluegreen-highlight">CALCULATOR[100*100]</span>
+</pre>
+
+The MRKL system would see the word `CALCULATOR` and plug `100*100` into the calculator app.
+This simple idea can easily be expanded to various symbolic computing tools.
+
+Consider the following additional examples of applications:
+
+- A chatbot that is able to respond to questions about a financial database by
+  extracting information to form a SQL query from a users' text.
+
+<pre>
+  <p>What is the price of Apple stock right now?</p>
+
+  <span className="bluegreen-highlight">
+    The current price is DATABASE[SELECT price FROM stock WHERE company =
+    "Apple" AND time = "now"].
+  </span>
+</pre>
+
+- A chatbot that is able to respond to questions about the weather by extracting
+  information from the prompt and using a weather API to retrieve the information.
+
+<pre>
+  <p>What is the weather like in New York?</p>
+
+  <span className="bluegreen-highlight">
+    The weather is WEATHER_API[New York].
+  </span>
+</pre>
+
+- Or even much more complex tasks that depend on multiple datasources, such as the
+  following:
+
+<div style={{ textAlign: "center" }}>
+  <Image
+    src="/docs/assets/advanced/mrkl_task.webp"
+    width={1600}
+    height={1331}
+    style={{ width: "500px", margin: "auto" }}
+  />
+</div>
+
+<div style={{ textAlign: "center" }}>Example MRKL System (AI21)</div>
+
+## An Example
+
+I have reproduced an example MRKL System from the original paper, using Dust.tt,
+linked [here](https://dust.tt/w/ddebdfcdde/a/98bdd65cb7).
+The system reads a math problem (e.g. `What is 20 times 5^6?`), extracts the numbers and the operations,
+and reformats them for a calculator app (e.g. `20*5^6`). It then sends the reformatted equation
+to Google's calculator app, and returns the result. Note that the original paper performs prompt tuning on the router (the LLM), but I do not in this example. Let's walk through how this works:
+
+First, I made a simple dataset in the Dust `Datasets` tab.
+
+<div style={{ textAlign: "center" }}>
+  <Image
+    src="/docs/assets/advanced/mrkl/dataset.webp"
+    width={2818}
+    height={820}
+    style={{ width: "750px", margin: "0" }}
+  />
+</div>
+
+Then, I switched to the `Specification` tab and loaded the dataset using an `input` block.
+
+<div style={{ textAlign: "center" }}>
+  <Image
+    src="/docs/assets/advanced/mrkl/load_dataset.webp"
+    width={2790}
+    height={508}
+    style={{ width: "750px", margin: "0" }}
+  />
+</div>
+
+Next, I created a `llm` block that extracts the numbers and operations. Notice how
+in the prompt I told it we would be using Google's calculator. The model I use (GPT-3)
+likely has some knowledge of Google's calculator from pretraining.
+
+<div style={{ textAlign: "center" }}>
+  <Image
+    src="/docs/assets/advanced/mrkl/model.webp"
+    width={2790}
+    height={960}
+    style={{ width: "750px", margin: "0" }}
+  />
+</div>
+
+Then, I made a `code` block, which runs some simple javascript code to remove
+spaces from the completion.
+
+<div style={{ textAlign: "center" }}>
+  <Image
+    src="/docs/assets/advanced/mrkl/extract.webp"
+    width={2790}
+    height={532}
+    style={{ width: "750px", margin: "0" }}
+  />
+</div>
+
+Finally, I made a `search` block that sends the reformatted equation to Google's calculator.
+
+<div style={{ textAlign: "center" }}>
+  <Image
+    src="/docs/assets/advanced/mrkl/search.webp"
+    width={2790}
+    height={1310}
+    style={{ width: "750px", margin: "0" }}
+  />
+</div>
+
+Below we can see the final results, which are all correct!
+
+<div style={{ textAlign: "center" }}>
+  <Image
+    src="/docs/assets/advanced/mrkl/final.webp"
+    width={2784}
+    height={494}
+    style={{ width: "750px", margin: "0" }}
+  />
+</div>
+
+Feel free to clone and experiment with this playground [here](https://dust.tt/w/ddebdfcdde/a/98bdd65cb7).
+
+## Notes
+
+MRKL was developed by [AI21](https://www.ai21.com/) and originally used their
+J-1 (Jurassic 1)(@lieberjurassic) LLM.
+
+## More
+
+See [this example](https://python.langchain.com/docs/modules/agents/how_to/mrkl) of a MRKL System
+built with LangChain.

(docs)/ar/docs/advanced_applications/overview/page.mdx

@@ -0,0 +1,8 @@
+export const metadata = { sidebar_position: 1, title: "🟢 Introduction" };
+
+# 🟢 Introduction
+
+We have seen a number of prompting/prompt engineering methods thus far.
+Now we will cover some advanced applications of prompting that can solve
+complex reasoning tasks by performing searches for information via the internet,
+or other external sources.

(docs)/ar/docs/advanced_applications/pal/page.mdx

@@ -0,0 +1,132 @@
+export const metadata = { sidebar_position: 4, title: "🟡 Code as Reasoning" };
+
+# 🟡 Code as Reasoning
+
+[Program-aided Language Models (PAL)](https://reasonwithpal.com)(@gao2022pal) are another example of a MRKL system.
+When given a question, PALs are able to **write code** that solves this question. They send the
+code to a programmatic runtime to get the result. PAL works in contrast to CoT; PAL's intermediate
+reasoning is code, while CoT's is natural language.
+
+<div style={{ textAlign: "center" }}>
+  <Image
+    src="/docs/assets/advanced/pal.webp"
+    width={1380}
+    height={1240}
+    style={{ width: "500px", margin: "auto" }}
+  />
+</div>
+
+<div style={{ textAlign: "center" }}>PAL Example (Gao et al.)</div>
+
+One important thing to note it that PAL actually interleaves natural language (NL) and code.
+In the above image, in blue are natural language reasoning that PAL generates. Although it
+is not shown in the image, PAL actually generates '\#' before each line of NL reasoning, so
+that they are interpreted as comments by the programmatic runtime.
+
+## Example
+
+Let's look at an example of PAL solving a math question. I use a 3-shot prompt,
+which is a simplified version of [this one](https://github.com/reasoning-machines/pal/blob/main/pal/prompt/math_prompts.py)(@gao2022pal).
+
+I will use langchain, a Python package for chaining LLM functionality for this. First, a few installations are needed:
+
+```python
+!pip install langchain==0.0.26
+!pip install openai
+from langchain.llms import OpenAI
+import os
+os.environ["OPENAI_API_KEY"] = "sk-YOUR_KEY_HERE"
+```
+
+Then, we can create an instance of GPT-3 davinci-002 (an API call happens when we use this object)
+
+```python
+llm = OpenAI(model_name='text-davinci-002', temperature=0)
+```
+
+Here is the few shot prompt:
+
+```python
+MATH_PROMPT = '''
+Q: There were nine computers in the server room. Five more computers were installed each day, from monday to thursday. How many computers are now in the server room?
+
+# solution in Python:
+"""There were nine computers in the server room. Five more computers were installed each day, from monday to thursday. How many computers are now in the server room?"""
+computers_initial = 9
+computers_per_day = 5
+num_days = 4  # 4 days between monday and thursday
+computers_added = computers_per_day * num_days
+computers_total = computers_initial + computers_added
+result = computers_total
+return result
+
+
+Q: Shawn has five toys. For Christmas, he got two toys each from his mom and dad. How many toys does he have now?
+
+# solution in Python:
+"""Shawn has five toys. For Christmas, he got two toys each from his mom and dad. How many toys does he have now?"""
+toys_initial = 5
+mom_toys = 2
+dad_toys = 2
+total_received = mom_toys + dad_toys
+total_toys = toys_initial + total_received
+result = total_toys
+
+
+Q: Jason had 20 lollipops. He gave Denny some lollipops. Now Jason has 12 lollipops. How many lollipops did Jason give to Denny?
+
+# solution in Python:
+"""Jason had 20 lollipops. He gave Denny some lollipops. Now Jason has 12 lollipops. How many lollipops did Jason give to Denny?"""
+jason_lollipops_initial = 20
+jason_lollipops_after = 12
+denny_lollipops = jason_lollipops_initial - jason_lollipops_after
+result = denny_lollipops
+
+Q: {question}
+
+# solution in Python:
+'''
+```
+
+Now we can pass the combined prompt to GPT-3.
+
+```python
+llm_out = llm(MATH_PROMPT.format(question=question))
+print(llm_out)
+```
+
+The output is:
+
+<pre>
+  <span className="bluegreen-highlight">
+    Emma took a 60 minute plane ride to seattle. She then took a 2 hour train
+    ride to portland, and then a 30 minute bus ride to vancouver. How long did
+    it take her to get to vancouver?
+    <br />
+    <br />
+    plane_ride = 60
+    <br />
+    train_ride = 2 * 60 # 2 hours in minutes
+    <br />
+    bus_ride = 30
+    <br />
+    total_time = plane_ride + train_ride + bus_ride
+    <br />
+    result = total_time
+  </span>
+</pre>
+
+Finally, we can pass this code to a Python runtime to get the answer:
+
+```python
+exec(llm_out)
+print(result)
+```
+
+The output is **210**, which is correct.
+
+See the Jupyter notebook for this example [here](https://github.com/trigaten/Learn_Prompting/tree/main/docs/code_examples/PAL.ipynb).
+
+## More
+
+Also see [PAL's colab example](https://colab.research.google.com/drive/1u4_RsdI0E79PCMDdcPiJUzYhdnjoXeXc?usp=sharing#scrollTo=Ba0ycacK4i1V).