You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/lab-1.5/README.md
+3Lines changed: 3 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -44,3 +44,6 @@ You may notice that your answer is slighty different then the screen shot above.
44
44
## Conclusion
45
45
46
46
**Congratulations!** Now you have Open-WebUI running and it's configured to work with `granite3.1-dense` and `ollama`. Move on to [Lab 2](https://ibm.github.io/opensource-ai-workshop/lab-2/) and have a chat with your model!
Copy file name to clipboardExpand all lines: docs/lab-1/README.md
+4-1Lines changed: 4 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -47,4 +47,7 @@ You may notice that your answer is slighty different then the screen shot above.
47
47
48
48
## Conclusion
49
49
50
-
**Congratulations!** Now you have AnythingLLM running and it's configured to work with `granite3.1-dense` and `ollama`. Move on to [Lab 2](https://ibm.github.io/opensource-ai-workshop/lab-2/) and have a chat with your model!
50
+
**Congratulations!** Now you have AnythingLLM running and it's configured to work with `granite3.1-dense` and `ollama`. Move on to [Lab 2](https://ibm.github.io/opensource-ai-workshop/lab-2/) and have a chat with your model!
Copy file name to clipboardExpand all lines: docs/lab-2/README.md
+3Lines changed: 3 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -105,3 +105,6 @@ in Batman's extensive history.
105
105
Spend as much time as you want asking your LLM about anything about any topic and exploring how you can alter its output to provide you with more interesting or satisfying responses.
106
106
107
107
When you are acquainted with your model, move on to [Lab 3](https://ibm.github.io/opensource-ai-workshop/lab-3/) to learn about Prompt Engineering.
Copy file name to clipboardExpand all lines: docs/lab-3/README.md
+11-8Lines changed: 11 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -44,7 +44,7 @@ Open a brand _new_ Workspace in AnythingLLM (or Open-WebUI) called "Learning Pro
44
44
These prompts don't have any previous data, structure, or guidelines provided with the request. Here's an example:
45
45
46
46
```
47
-
I want to explore pasta making recipes.
47
+
I want to explore pasta making recipes.
48
48
Do you have any suggestions for recipes that are unique and challenging?
49
49
```
50
50
@@ -57,7 +57,7 @@ Try it for yourself, did you get a different response? Think about how the respo
57
57
As a follow-up, I'll ask for the recipe to make the "Homemade Ravioli" option in the response I received:
58
58
59
59
```
60
-
I do like some homemade ravioli.
60
+
I do like some homemade ravioli.
61
61
What is the spinach, ricotta and cheese recipe you suggest?
62
62
```
63
63
@@ -78,13 +78,13 @@ In the following examples, we'll add more guidance in our prompt. By providing *
78
78
Take the provided prompts, and replace the [words] in brackets with your own choices. Get creative with it!
79
79
80
80
```
81
-
I want you to act as a customer support assistant who is [characteristic].
81
+
I want you to act as a customer support assistant who is [characteristic].
82
82
How would you respond to [text] as a representative of our [type] company?
83
83
```
84
84
85
85
My version will be:
86
86
```
87
-
I want you to act as a customer support assistant who is an expert in shipping logistics.
87
+
I want you to act as a customer support assistant who is an expert in shipping logistics.
88
88
How would you respond to client who has had their freight lost as a representative of our company?
89
89
```
90
90
@@ -93,10 +93,10 @@ How would you respond to client who has had their freight lost as a representati
93
93
That's not a satisfactory or interesting response, right? We need to interate on it, and provide more context about the client, like what they may have lost. **Tip: always think about adding more context!**
94
94
95
95
```
96
-
The freight they lost was an industrial refrigerator, from Burbank, California to Kanas City, MO.
97
-
I need you to write out an apology letter, with reference to the shipping order #00234273
98
-
and the help line of 1-800-347-2845, with a discount code of OPPSWEDIDITAGAIN for 15% off
99
-
shipping their next order. Mention that sometimes, the trucks have accidents and need
96
+
The freight they lost was an industrial refrigerator, from Burbank, California to Kanas City, MO.
97
+
I need you to write out an apology letter, with reference to the shipping order #00234273
98
+
and the help line of 1-800-347-2845, with a discount code of OPPSWEDIDITAGAIN for 15% off
99
+
shipping their next order. Mention that sometimes, the trucks have accidents and need
100
100
to be repaired and we should be able to reach out in a couple weeks.
101
101
```
102
102
@@ -107,3 +107,6 @@ So much better! By providing more context and more insight into what you are exp
107
107
## Conclusion
108
108
109
109
Now that you know the basics of prompt engineering and simple techniques you can use to level-up your prompts, let's move on to [Lab 4](https://ibm.github.io/opensource-ai-workshop/lab-4/) and apply what you've learned with some exercises.
Copy file name to clipboardExpand all lines: docs/lab-4/README.md
+12-9Lines changed: 12 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -29,8 +29,8 @@ Format the sentences like a list.
29
29
30
30
## 2. Extract Summary Topics
31
31
32
-
**Prompt a model to extract a short, bulleted summary from a meeting transcript.**
33
-
The goal is to turn raw dialogue into clear, actionable notes — just like you'd want after a real meeting.
32
+
**Prompt a model to extract a short, bulleted summary from a meeting transcript.**
33
+
The goal is to turn raw dialogue into clear, actionable notes — just like you'd want after a real meeting.
34
34
35
35
You can use the following meeting transcripts.
36
36
@@ -116,10 +116,10 @@ over the fields and forests.
116
116
```
117
117
118
118
```
119
-
It's windy as the sun sets over the horizon, casting a warm glow on the
119
+
It's windy as the sun sets over the horizon, casting a warm glow on the
120
120
landscape.
121
121
122
-
A gentle breeze rustles the leaves of the trees as the sun begins to set
122
+
A gentle breeze rustles the leaves of the trees as the sun begins to set
123
123
and colour the landscape.
124
124
```
125
125
@@ -166,19 +166,19 @@ Core Skills: content strategy, SEO optimization, team leadership, data analytics
166
166
Past Roles:
167
167
- Social Media Manager at BrightSpark (2 years)
168
168
- Content Writer at BuzzTone Agency (1 year)
169
-
Education:
169
+
Education:
170
170
- B.A. in Communications
171
171
```
172
172
173
173
<details>
174
174
<summary> Show example prompt </summary>
175
175
```
176
-
The following text is my resume for my career up
176
+
The following text is my resume for my career up
177
177
until my most recent job. I am [current job] with
178
-
[years of experience] considered a highly skilled
178
+
[years of experience] considered a highly skilled
179
179
individual in [core skill set]. I want to build a
180
180
two paragraph explanation about why someone should
181
-
hire me for a role with both my current skill set
181
+
hire me for a role with both my current skill set
182
182
and previous experience.
183
183
```
184
184
@@ -195,7 +195,7 @@ If you're familiar with the role-playing game Dungeons & Dragons, this excercise
195
195
196
196
**Write a prompt that you would give to an AI to generate a one-shot D&D adventure**
197
197
198
-
Focus on providing enough detail to create a cohesive story for a one-session gameplay experience.
198
+
Focus on providing enough detail to create a cohesive story for a one-session gameplay experience.
199
199
Think about the environment, the objectives, challenges, and the final boss encounter—all while keeping it concise and exciting for the players.
200
200
201
201
<details>
@@ -213,3 +213,6 @@ The best part of this prompt is that you can take the output and extend or short
213
213
## Conclusion
214
214
215
215
Well done! By completing these exercises, you're well on your way to being a prompt expert. In [Lab 5](https://ibm.github.io/opensource-ai-workshop/lab-5/), we'll move towards code-generation and learn how to use a local coding assistant.
Copy file name to clipboardExpand all lines: docs/lab-6/README.md
+4-1Lines changed: 4 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -12,7 +12,7 @@ First, get comfortable with Continue. For example, if you prefer that your local
12
12
13
13
You can also take a look at the [Continue documentation](https://docs.continue.dev/chat/how-to-use-it), or at least have it open in case you want to refer to it.
14
14
15
-
Now that our local AI co-pilot is up and running, let’s put it to work. The following examples will focus on `python`, but the same approach applies to other languages like `go`, `javascript`, or `rust`.
15
+
Now that our local AI co-pilot is up and running, let’s put it to work. The following examples will focus on `python`, but the same approach applies to other languages like `go`, `javascript`, or `rust`.
16
16
17
17
A key part of learning to use this technology effectively is exploring the boundaries of what it can and can’t do.
18
18
@@ -112,3 +112,6 @@ Continue also provides the ability to automatically add comments to code. Try it
112
112
## Conclusion
113
113
114
114
This lab was all about using our local, open-source AI co-pilot to write complex code in Python. By combining Continue and Granite-Code, we were able to generate code, explain functions, write tests, and add comments to our code!
0 commit comments