From 33d40684655ffe0afdccc67915e595bdcbae0cb5 Mon Sep 17 00:00:00 2001
From: Ado Kukic <kukicadnan@gmail.com>
Date: Tue, 5 Nov 2024 11:59:41 -0800
Subject: [PATCH 1/4] Hackathon - FAQs

---
 docs/cody/faq.mdx | 1 +
 1 file changed, 1 insertion(+)

diff --git a/docs/cody/faq.mdx b/docs/cody/faq.mdx
index 4fcacca34..3188ff434 100644
--- a/docs/cody/faq.mdx
+++ b/docs/cody/faq.mdx
@@ -1,3 +1,4 @@
+{/* Hackathon */}
 # Cody FAQs
 
 <p className="subtitle">Find answers to the most common questions about Cody.</p>

From 42cd08f2c35591bc2d02650af36e2c6b7b44c135 Mon Sep 17 00:00:00 2001
From: Justin Dorfman <justindorfman@gmail.com>
Date: Tue, 12 Nov 2024 05:28:15 -0800
Subject: [PATCH 2/4] feat(docs): Add FAQ for OpenAI o1 best practices

- Provide guidance on context management, model selection, prompting strategy, response time, and quality for using OpenAI o1 models
- Document known technical limitations of o1 models
---
 docs/cody/faq.mdx | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/docs/cody/faq.mdx b/docs/cody/faq.mdx
index 3188ff434..0449c3ccf 100644
--- a/docs/cody/faq.mdx
+++ b/docs/cody/faq.mdx
@@ -137,3 +137,47 @@ cody chat --model '$name_of_the_model' -m 'Hi Cody!'
 ```
 
 For example, to use Claude 3.5 Sonnet, you'd pass the following command in your terminal, `cody chat --model 'claude-3.5-sonnet' -m 'Hi Cody!'
+
+## OpenAI o1
+
+### What are OpenAI o1 best practices?
+
+#### Context Management
+
+- Provide focused, relevant context
+- Use file references strategically
+- Keep initial requests concise
+
+#### Model Selection
+
+- O1-preview: Best for complex reasoning and planning
+- O1-mini: More reliable for straightforward tasks
+- Sonnet 3.5: Better for tasks requiring longer outputs
+
+#### Prompting Strategy
+
+- Be specific and direct
+- Include complete requirements upfront
+- Request brief responses when possible
+- Use step-by-step approach for complex tasks
+
+#### Response Time
+
+- Start with smaller contexts
+- Use O1-mini for faster responses
+- Consider breaking complex tasks into stages
+
+#### Quality
+
+- Provide clear acceptance criteria
+- Include relevant context but avoid excess
+- Use specific examples when possible
+
+### What are the known limitations?
+
+#### Technical Constraints
+
+- 45k input token limit
+- 4k output token limit
+- No streaming responses for O1 series
+- Limited context window

From 217cb49445eee72f9a627d307a05eed3f43dac07 Mon Sep 17 00:00:00 2001
From: Maedah Batool <me@MaedahBatool.com>
Date: Tue, 12 Nov 2024 18:43:55 -0800
Subject: [PATCH 3/4] rmv banner

---
 docs/cody/faq.mdx | 1 -
 1 file changed, 1 deletion(-)

diff --git a/docs/cody/faq.mdx b/docs/cody/faq.mdx
index 0449c3ccf..502befca9 100644
--- a/docs/cody/faq.mdx
+++ b/docs/cody/faq.mdx
@@ -1,4 +1,3 @@
-{/* Hackathon */}
 # Cody FAQs
 
 <p className="subtitle">Find answers to the most common questions about Cody.</p>

From 5c62977676a60d9c91e42c688bc0dc57c39f43e4 Mon Sep 17 00:00:00 2001
From: Maedah Batool <me@MaedahBatool.com>
Date: Tue, 12 Nov 2024 18:46:04 -0800
Subject: [PATCH 4/4] Add imporvements

---
 docs/cody/faq.mdx | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/docs/cody/faq.mdx b/docs/cody/faq.mdx
index 502befca9..fee3d1dff 100644
--- a/docs/cody/faq.mdx
+++ b/docs/cody/faq.mdx
@@ -149,9 +149,9 @@ For example, to use Claude 3.5 Sonnet, you'd pass the following command in your
 
 #### Model Selection
 
-- O1-preview: Best for complex reasoning and planning
-- O1-mini: More reliable for straightforward tasks
-- Sonnet 3.5: Better for tasks requiring longer outputs
+- **o1-preview**: Best for complex reasoning and planning
+- **o1-mini**: More reliable for straightforward tasks
+- **Sonnet 3.5**: Better for tasks requiring longer outputs
 
 #### Prompting Strategy
 
@@ -163,7 +163,7 @@ For example, to use Claude 3.5 Sonnet, you'd pass the following command in your
 #### Response Time
 
 - Start with smaller contexts
-- Use O1-mini for faster responses
+- Use o1-mini for faster responses
 - Consider breaking complex tasks into stages
 
 #### Quality
@@ -178,5 +178,5 @@ For example, to use Claude 3.5 Sonnet, you'd pass the following command in your
 
 - 45k input token limit
 - 4k output token limit
-- No streaming responses for O1 series
+- No streaming responses for o1 series
 - Limited context window