From e0522b92cfa80491718de07928ce6a31850dab70 Mon Sep 17 00:00:00 2001
From: Nate Sesti <sestinj@gmail.com>
Date: Wed, 13 Sep 2023 23:03:58 -0700
Subject: feat: :sparkles: verify_ssl option for all LLMs

---
 docs/docs/reference/Models/anthropic.md          | 2 +-
 docs/docs/reference/Models/ggml.md               | 4 ++--
 docs/docs/reference/Models/hf_inference_api.md   | 2 +-
 docs/docs/reference/Models/hf_tgi.md             | 4 ++--
 docs/docs/reference/Models/llamacpp.md           | 4 ++--
 docs/docs/reference/Models/maybe_proxy_openai.md | 2 +-
 docs/docs/reference/Models/ollama.md             | 2 +-
 docs/docs/reference/Models/openai.md             | 4 ++--
 docs/docs/reference/Models/queued.md             | 2 +-
 docs/docs/reference/Models/replicate.md          | 2 +-
 docs/docs/reference/Models/text_gen_interface.md | 4 ++--
 docs/docs/reference/Models/together.md           | 4 ++--
 docs/docs/reference/config.md                    | 2 +-
 13 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'docs')

diff --git a/docs/docs/reference/Models/anthropic.md b/docs/docs/reference/Models/anthropic.md
index 8fec179a..25f258ae 100644
--- a/docs/docs/reference/Models/anthropic.md
+++ b/docs/docs/reference/Models/anthropic.md
@@ -25,4 +25,4 @@ Claude 2 is not yet publicly released. You can request early access [here](https
 
 ### Inherited Properties
 
-<ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={true} default=""/><ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;claude-2&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="claude-2"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{}"/>
\ No newline at end of file
+<ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={true} default=""/><ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;claude-2&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="claude-2"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{}"/>
\ No newline at end of file
diff --git a/docs/docs/reference/Models/ggml.md b/docs/docs/reference/Models/ggml.md
index fbaf12d0..239485c8 100644
--- a/docs/docs/reference/Models/ggml.md
+++ b/docs/docs/reference/Models/ggml.md
@@ -23,8 +23,8 @@ config = ContinueConfig(
 
 ## Properties
 
-<ClassPropertyRef name='server_url' details='{&quot;title&quot;: &quot;Server Url&quot;, &quot;description&quot;: &quot;URL of the OpenAI-compatible server where the model is being served&quot;, &quot;default&quot;: &quot;http://localhost:8000&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="http://localhost:8000"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether SSL certificates should be verified when making the HTTP request&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='ca_bundle_path' details='{&quot;title&quot;: &quot;Ca Bundle Path&quot;, &quot;description&quot;: &quot;Path to a custom CA bundle to use when making the HTTP request&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
+<ClassPropertyRef name='server_url' details='{&quot;title&quot;: &quot;Server Url&quot;, &quot;description&quot;: &quot;URL of the OpenAI-compatible server where the model is being served&quot;, &quot;default&quot;: &quot;http://localhost:8000&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="http://localhost:8000"/><ClassPropertyRef name='proxy' details='{&quot;title&quot;: &quot;Proxy&quot;, &quot;description&quot;: &quot;Proxy URL to use when making the HTTP request&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='ca_bundle_path' details='{&quot;title&quot;: &quot;Ca Bundle Path&quot;, &quot;description&quot;: &quot;Path to a custom CA bundle to use when making the HTTP request&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
 
 ### Inherited Properties
 
-<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to use (optional for the GGML class)&quot;, &quot;default&quot;: &quot;ggml&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="ggml"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
+<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to use (optional for the GGML class)&quot;, &quot;default&quot;: &quot;ggml&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="ggml"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
diff --git a/docs/docs/reference/Models/hf_inference_api.md b/docs/docs/reference/Models/hf_inference_api.md
index 605813be..e3f1ed7c 100644
--- a/docs/docs/reference/Models/hf_inference_api.md
+++ b/docs/docs/reference/Models/hf_inference_api.md
@@ -26,4 +26,4 @@ config = ContinueConfig(
 
 ### Inherited Properties
 
-<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to use (optional for the HuggingFaceInferenceAPI class)&quot;, &quot;default&quot;: &quot;Hugging Face Inference API&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="Hugging Face Inference API"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
+<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to use (optional for the HuggingFaceInferenceAPI class)&quot;, &quot;default&quot;: &quot;Hugging Face Inference API&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="Hugging Face Inference API"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
diff --git a/docs/docs/reference/Models/hf_tgi.md b/docs/docs/reference/Models/hf_tgi.md
index b6eb61d7..f44c9b24 100644
--- a/docs/docs/reference/Models/hf_tgi.md
+++ b/docs/docs/reference/Models/hf_tgi.md
@@ -8,8 +8,8 @@ import ClassPropertyRef from '@site/src/components/ClassPropertyRef.tsx';
 
 ## Properties
 
-<ClassPropertyRef name='server_url' details='{&quot;title&quot;: &quot;Server Url&quot;, &quot;description&quot;: &quot;URL of your TGI server&quot;, &quot;default&quot;: &quot;http://localhost:8080&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="http://localhost:8080"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether SSL certificates should be verified when making the HTTP request&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/>
+<ClassPropertyRef name='server_url' details='{&quot;title&quot;: &quot;Server Url&quot;, &quot;description&quot;: &quot;URL of your TGI server&quot;, &quot;default&quot;: &quot;http://localhost:8080&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="http://localhost:8080"/>
 
 ### Inherited Properties
 
-<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;huggingface-tgi&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="huggingface-tgi"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
+<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;huggingface-tgi&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="huggingface-tgi"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
diff --git a/docs/docs/reference/Models/llamacpp.md b/docs/docs/reference/Models/llamacpp.md
index 0bb06e74..82260035 100644
--- a/docs/docs/reference/Models/llamacpp.md
+++ b/docs/docs/reference/Models/llamacpp.md
@@ -27,8 +27,8 @@ config = ContinueConfig(
 
 ## Properties
 
-<ClassPropertyRef name='server_url' details='{&quot;title&quot;: &quot;Server Url&quot;, &quot;description&quot;: &quot;URL of the server&quot;, &quot;default&quot;: &quot;http://localhost:8080&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="http://localhost:8080"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether SSL certificates should be verified when making the HTTP request&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='llama_cpp_args' details='{&quot;title&quot;: &quot;Llama Cpp Args&quot;, &quot;description&quot;: &quot;A list of additional arguments to pass to llama.cpp. See [here](https://github.com/ggerganov/llama.cpp/tree/master/examples/server#api-endpoints) for the complete catalog of options.&quot;, &quot;default&quot;: {&quot;stop&quot;: [&quot;[INST]&quot;]}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;stop&#x27;: [&#x27;[INST]&#x27;]}"/>
+<ClassPropertyRef name='server_url' details='{&quot;title&quot;: &quot;Server Url&quot;, &quot;description&quot;: &quot;URL of the server&quot;, &quot;default&quot;: &quot;http://localhost:8080&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="http://localhost:8080"/><ClassPropertyRef name='llama_cpp_args' details='{&quot;title&quot;: &quot;Llama Cpp Args&quot;, &quot;description&quot;: &quot;A list of additional arguments to pass to llama.cpp. See [here](https://github.com/ggerganov/llama.cpp/tree/master/examples/server#api-endpoints) for the complete catalog of options.&quot;, &quot;default&quot;: {&quot;stop&quot;: [&quot;[INST]&quot;]}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;stop&#x27;: [&#x27;[INST]&#x27;]}"/>
 
 ### Inherited Properties
 
-<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;llamacpp&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="llamacpp"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
+<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;llamacpp&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="llamacpp"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
diff --git a/docs/docs/reference/Models/maybe_proxy_openai.md b/docs/docs/reference/Models/maybe_proxy_openai.md
index 22ac2382..712f1cba 100644
--- a/docs/docs/reference/Models/maybe_proxy_openai.md
+++ b/docs/docs/reference/Models/maybe_proxy_openai.md
@@ -33,4 +33,4 @@ These classes support any models available through the OpenAI API, assuming your
 
 ### Inherited Properties
 
-<ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;type&quot;: &quot;string&quot;}' required={true} default=""/><ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
+<ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;type&quot;: &quot;string&quot;}' required={true} default=""/><ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
diff --git a/docs/docs/reference/Models/ollama.md b/docs/docs/reference/Models/ollama.md
index 9792ee52..234db171 100644
--- a/docs/docs/reference/Models/ollama.md
+++ b/docs/docs/reference/Models/ollama.md
@@ -23,4 +23,4 @@ config = ContinueConfig(
 
 ### Inherited Properties
 
-<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;llama2&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="llama2"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
+<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;llama2&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="llama2"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
diff --git a/docs/docs/reference/Models/openai.md b/docs/docs/reference/Models/openai.md
index 0ade1a8f..ec5d2955 100644
--- a/docs/docs/reference/Models/openai.md
+++ b/docs/docs/reference/Models/openai.md
@@ -32,8 +32,8 @@ Options for serving models locally with an OpenAI-compatible server include:
 
 ## Properties
 
-<ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='ca_bundle_path' details='{&quot;title&quot;: &quot;Ca Bundle Path&quot;, &quot;description&quot;: &quot;Path to CA bundle to use for requests.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='proxy' details='{&quot;title&quot;: &quot;Proxy&quot;, &quot;description&quot;: &quot;Proxy URL to use for requests.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='api_base' details='{&quot;title&quot;: &quot;Api Base&quot;, &quot;description&quot;: &quot;OpenAI API base URL.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='api_type' details='{&quot;title&quot;: &quot;Api Type&quot;, &quot;description&quot;: &quot;OpenAI API type.&quot;, &quot;enum&quot;: [&quot;azure&quot;, &quot;openai&quot;], &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='api_version' details='{&quot;title&quot;: &quot;Api Version&quot;, &quot;description&quot;: &quot;OpenAI API version. For use with Azure OpenAI Service.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='engine' details='{&quot;title&quot;: &quot;Engine&quot;, &quot;description&quot;: &quot;OpenAI engine. For use with Azure OpenAI Service.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
+<ClassPropertyRef name='ca_bundle_path' details='{&quot;title&quot;: &quot;Ca Bundle Path&quot;, &quot;description&quot;: &quot;Path to CA bundle to use for requests.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='proxy' details='{&quot;title&quot;: &quot;Proxy&quot;, &quot;description&quot;: &quot;Proxy URL to use for requests.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='api_base' details='{&quot;title&quot;: &quot;Api Base&quot;, &quot;description&quot;: &quot;OpenAI API base URL.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='api_type' details='{&quot;title&quot;: &quot;Api Type&quot;, &quot;description&quot;: &quot;OpenAI API type.&quot;, &quot;enum&quot;: [&quot;azure&quot;, &quot;openai&quot;], &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='api_version' details='{&quot;title&quot;: &quot;Api Version&quot;, &quot;description&quot;: &quot;OpenAI API version. For use with Azure OpenAI Service.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='engine' details='{&quot;title&quot;: &quot;Engine&quot;, &quot;description&quot;: &quot;OpenAI engine. For use with Azure OpenAI Service.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
 
 ### Inherited Properties
 
-<ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;type&quot;: &quot;string&quot;}' required={true} default=""/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;OpenAI API key&quot;, &quot;type&quot;: &quot;string&quot;}' required={true} default=""/><ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{}"/>
\ No newline at end of file
+<ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;type&quot;: &quot;string&quot;}' required={true} default=""/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;OpenAI API key&quot;, &quot;type&quot;: &quot;string&quot;}' required={true} default=""/><ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{}"/>
\ No newline at end of file
diff --git a/docs/docs/reference/Models/queued.md b/docs/docs/reference/Models/queued.md
index e253da09..b38f78cc 100644
--- a/docs/docs/reference/Models/queued.md
+++ b/docs/docs/reference/Models/queued.md
@@ -25,4 +25,4 @@ config = ContinueConfig(
 
 ### Inherited Properties
 
-<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;queued&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="queued"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
+<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;queued&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="queued"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
diff --git a/docs/docs/reference/Models/replicate.md b/docs/docs/reference/Models/replicate.md
index 0c93a758..05a804f0 100644
--- a/docs/docs/reference/Models/replicate.md
+++ b/docs/docs/reference/Models/replicate.md
@@ -28,4 +28,4 @@ If you don't specify the `model` parameter, it will default to `replicate/llama-
 
 ### Inherited Properties
 
-<ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;Replicate API key&quot;, &quot;type&quot;: &quot;string&quot;}' required={true} default=""/><ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/>
\ No newline at end of file
+<ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;Replicate API key&quot;, &quot;type&quot;: &quot;string&quot;}' required={true} default=""/><ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/>
\ No newline at end of file
diff --git a/docs/docs/reference/Models/text_gen_interface.md b/docs/docs/reference/Models/text_gen_interface.md
index 21404960..2d0dd8b5 100644
--- a/docs/docs/reference/Models/text_gen_interface.md
+++ b/docs/docs/reference/Models/text_gen_interface.md
@@ -21,8 +21,8 @@ config = ContinueConfig(
 
 ## Properties
 
-<ClassPropertyRef name='server_url' details='{&quot;title&quot;: &quot;Server Url&quot;, &quot;description&quot;: &quot;URL of your TextGenUI server&quot;, &quot;default&quot;: &quot;http://localhost:5000&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="http://localhost:5000"/><ClassPropertyRef name='streaming_url' details='{&quot;title&quot;: &quot;Streaming Url&quot;, &quot;description&quot;: &quot;URL of your TextGenUI streaming server (separate from main server URL)&quot;, &quot;default&quot;: &quot;http://localhost:5005&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="http://localhost:5005"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/>
+<ClassPropertyRef name='server_url' details='{&quot;title&quot;: &quot;Server Url&quot;, &quot;description&quot;: &quot;URL of your TextGenUI server&quot;, &quot;default&quot;: &quot;http://localhost:5000&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="http://localhost:5000"/><ClassPropertyRef name='streaming_url' details='{&quot;title&quot;: &quot;Streaming Url&quot;, &quot;description&quot;: &quot;URL of your TextGenUI streaming server (separate from main server URL)&quot;, &quot;default&quot;: &quot;http://localhost:5005&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="http://localhost:5005"/>
 
 ### Inherited Properties
 
-<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;text-gen-ui&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="text-gen-ui"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
+<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;text-gen-ui&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="text-gen-ui"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Here is the code before editing:\n```\n{{code_to_edit}}\n```\n\nHere is the edit requested:\n\&quot;{{user_input}}\&quot;\n\nHere is the code after editing:\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Here is the code before editing:\n```\n{{code_to_edit}}\n```\n\nHere is the edit requested:\n&quot;{{user_input}}&quot;\n\nHere is the code after editing:\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/>
\ No newline at end of file
diff --git a/docs/docs/reference/Models/together.md b/docs/docs/reference/Models/together.md
index ec1ebb9c..dcb9e76c 100644
--- a/docs/docs/reference/Models/together.md
+++ b/docs/docs/reference/Models/together.md
@@ -23,8 +23,8 @@ config = ContinueConfig(
 
 ## Properties
 
-<ClassPropertyRef name='base_url' details='{&quot;title&quot;: &quot;Base Url&quot;, &quot;description&quot;: &quot;The base URL for your Together API instance&quot;, &quot;default&quot;: &quot;https://api.together.xyz&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="https://api.together.xyz"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether SSL certificates should be verified when making the HTTP request&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/>
+<ClassPropertyRef name='base_url' details='{&quot;title&quot;: &quot;Base Url&quot;, &quot;description&quot;: &quot;The base URL for your Together API instance&quot;, &quot;default&quot;: &quot;https://api.together.xyz&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="https://api.together.xyz"/>
 
 ### Inherited Properties
 
-<ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;Together API key&quot;, &quot;type&quot;: &quot;string&quot;}' required={true} default=""/><ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;togethercomputer/RedPajama-INCITE-7B-Instruct&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="togethercomputer/RedPajama-INCITE-7B-Instruct"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/>
\ No newline at end of file
+<ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;Together API key&quot;, &quot;type&quot;: &quot;string&quot;}' required={true} default=""/><ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to be used (e.g. gpt-4, codellama)&quot;, &quot;default&quot;: &quot;togethercomputer/RedPajama-INCITE-7B-Instruct&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="togethercomputer/RedPajama-INCITE-7B-Instruct"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/>
\ No newline at end of file
diff --git a/docs/docs/reference/config.md b/docs/docs/reference/config.md
index b26d8cde..54664a7e 100644
--- a/docs/docs/reference/config.md
+++ b/docs/docs/reference/config.md
@@ -8,7 +8,7 @@ Continue can be deeply customized by editing the `ContinueConfig` object in `~/.
 
 ## Properties
 
-<ClassPropertyRef name='steps_on_startup' details='{&quot;title&quot;: &quot;Steps On Startup&quot;, &quot;description&quot;: &quot;Steps that will be automatically run at the beginning of a new session&quot;, &quot;default&quot;: [], &quot;type&quot;: &quot;array&quot;, &quot;items&quot;: {&quot;$ref&quot;: &quot;#/definitions/Step&quot;}}' required={false} default="[]"/><ClassPropertyRef name='disallowed_steps' details='{&quot;title&quot;: &quot;Disallowed Steps&quot;, &quot;description&quot;: &quot;Steps that are not allowed to be run, and will be skipped if attempted&quot;, &quot;default&quot;: [], &quot;type&quot;: &quot;array&quot;, &quot;items&quot;: {&quot;type&quot;: &quot;string&quot;}}' required={false} default="[]"/><ClassPropertyRef name='allow_anonymous_telemetry' details='{&quot;title&quot;: &quot;Allow Anonymous Telemetry&quot;, &quot;description&quot;: &quot;If this field is set to True, we will collect anonymous telemetry as described in the documentation page on telemetry. If set to False, we will not collect any data.&quot;, &quot;default&quot;: true, &quot;type&quot;: &quot;boolean&quot;}' required={false} default="True"/><ClassPropertyRef name='models' details='{&quot;title&quot;: &quot;Models&quot;, &quot;description&quot;: &quot;Configuration for the models used by Continue. Read more about how to configure models in the documentation.&quot;, &quot;default&quot;: {&quot;default&quot;: {&quot;title&quot;: null, &quot;system_message&quot;: null, &quot;context_length&quot;: 2048, &quot;model&quot;: &quot;gpt-4&quot;, &quot;timeout&quot;: 300, &quot;prompt_templates&quot;: {}, &quot;api_key&quot;: null, &quot;llm&quot;: null, &quot;class_name&quot;: &quot;MaybeProxyOpenAI&quot;}, &quot;small&quot;: null, &quot;medium&quot;: {&quot;title&quot;: null, &quot;system_message&quot;: null, &quot;context_length&quot;: 2048, &quot;model&quot;: &quot;gpt-3.5-turbo&quot;, &quot;timeout&quot;: 300, &quot;prompt_templates&quot;: {}, &quot;api_key&quot;: null, &quot;llm&quot;: null, &quot;class_name&quot;: &quot;MaybeProxyOpenAI&quot;}, &quot;large&quot;: null, &quot;edit&quot;: null, &quot;chat&quot;: null, &quot;unused&quot;: []}, &quot;allOf&quot;: [{&quot;$ref&quot;: &quot;#/definitions/Models&quot;}]}' required={false} default="{&#x27;default&#x27;: {&#x27;title&#x27;: None, &#x27;system_message&#x27;: None, &#x27;context_length&#x27;: 2048, &#x27;model&#x27;: &#x27;gpt-4&#x27;, &#x27;timeout&#x27;: 300, &#x27;prompt_templates&#x27;: {}, &#x27;api_key&#x27;: None, &#x27;llm&#x27;: None, &#x27;class_name&#x27;: &#x27;MaybeProxyOpenAI&#x27;}, &#x27;small&#x27;: None, &#x27;medium&#x27;: {&#x27;title&#x27;: None, &#x27;system_message&#x27;: None, &#x27;context_length&#x27;: 2048, &#x27;model&#x27;: &#x27;gpt-3.5-turbo&#x27;, &#x27;timeout&#x27;: 300, &#x27;prompt_templates&#x27;: {}, &#x27;api_key&#x27;: None, &#x27;llm&#x27;: None, &#x27;class_name&#x27;: &#x27;MaybeProxyOpenAI&#x27;}, &#x27;large&#x27;: None, &#x27;edit&#x27;: None, &#x27;chat&#x27;: None, &#x27;unused&#x27;: []}"/><ClassPropertyRef name='temperature' details='{&quot;title&quot;: &quot;Temperature&quot;, &quot;description&quot;: &quot;The temperature parameter for sampling from the LLM. Higher temperatures will result in more random output, while lower temperatures will result in more predictable output. This value ranges from 0 to 1.&quot;, &quot;default&quot;: 0.5, &quot;type&quot;: &quot;number&quot;}' required={false} default="0.5"/><ClassPropertyRef name='custom_commands' details='{&quot;title&quot;: &quot;Custom Commands&quot;, &quot;description&quot;: &quot;An array of custom commands that allow you to reuse prompts. Each has name, description, and prompt properties. When you enter /&lt;name&gt; in the text input, it will act as a shortcut to the prompt.&quot;, &quot;default&quot;: [{&quot;name&quot;: &quot;test&quot;, &quot;prompt&quot;: &quot;Write a comprehensive set of unit tests for the selected code. It should setup, run tests that check for correctness including important edge cases, and teardown. Ensure that the tests are complete and sophisticated. Give the tests just as chat output, don&#x27;t edit any file.&quot;, &quot;description&quot;: &quot;This is an example custom command. Use /config to edit it and create more&quot;}], &quot;type&quot;: &quot;array&quot;, &quot;items&quot;: {&quot;$ref&quot;: &quot;#/definitions/CustomCommand&quot;}}' required={false} default="[{&#x27;name&#x27;: &#x27;test&#x27;, &#x27;prompt&#x27;: &quot;Write a comprehensive set of unit tests for the selected code. It should setup, run tests that check for correctness including important edge cases, and teardown. Ensure that the tests are complete and sophisticated. Give the tests just as chat output, don&#x27;t edit any file.&quot;, &#x27;description&#x27;: &#x27;This is an example custom command. Use /config to edit it and create more&#x27;}]"/><ClassPropertyRef name='slash_commands' details='{&quot;title&quot;: &quot;Slash Commands&quot;, &quot;description&quot;: &quot;An array of slash commands that let you map custom Steps to a shortcut.&quot;, &quot;default&quot;: [], &quot;type&quot;: &quot;array&quot;, &quot;items&quot;: {&quot;$ref&quot;: &quot;#/definitions/SlashCommand&quot;}}' required={false} default="[]"/><ClassPropertyRef name='on_traceback' details='{&quot;title&quot;: &quot;On Traceback&quot;, &quot;description&quot;: &quot;The step that will be run when a traceback is detected (when you use the shortcut cmd+shift+R)&quot;, &quot;allOf&quot;: [{&quot;$ref&quot;: &quot;#/definitions/Step&quot;}]}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='policy_override' details='{&quot;title&quot;: &quot;Policy Override&quot;, &quot;description&quot;: &quot;A Policy object that can be used to override the default behavior of Continue, for example in order to build custom agents that take multiple steps at a time.&quot;, &quot;allOf&quot;: [{&quot;$ref&quot;: &quot;#/definitions/Policy&quot;}]}' required={false} default=""/><ClassPropertyRef name='context_providers' details='{&quot;title&quot;: &quot;Context Providers&quot;, &quot;description&quot;: &quot;A list of ContextProvider objects that can be used to provide context to the LLM by typing &#x27;@&#x27;. Read more about ContextProviders in the documentation.&quot;, &quot;default&quot;: [], &quot;type&quot;: &quot;array&quot;, &quot;items&quot;: {&quot;$ref&quot;: &quot;#/definitions/ContextProvider&quot;}}' required={false} default="[]"/><ClassPropertyRef name='user_token' details='{&quot;title&quot;: &quot;User Token&quot;, &quot;description&quot;: &quot;An optional token to identify the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='data_server_url' details='{&quot;title&quot;: &quot;Data Server Url&quot;, &quot;description&quot;: &quot;The URL of the server where development data is sent. No data is sent unless a valid user token is provided.&quot;, &quot;default&quot;: &quot;https://us-west1-autodebug.cloudfunctions.net&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="https://us-west1-autodebug.cloudfunctions.net"/><ClassPropertyRef name='disable_summaries' details='{&quot;title&quot;: &quot;Disable Summaries&quot;, &quot;description&quot;: &quot;If set to `True`, Continue will not generate summaries for each Step. This can be useful if you want to save on compute.&quot;, &quot;default&quot;: false, &quot;type&quot;: &quot;boolean&quot;}' required={false} default="False"/>
+<ClassPropertyRef name='steps_on_startup' details='{&quot;title&quot;: &quot;Steps On Startup&quot;, &quot;description&quot;: &quot;Steps that will be automatically run at the beginning of a new session&quot;, &quot;default&quot;: [], &quot;type&quot;: &quot;array&quot;, &quot;items&quot;: {&quot;$ref&quot;: &quot;#/definitions/Step&quot;}}' required={false} default="[]"/><ClassPropertyRef name='disallowed_steps' details='{&quot;title&quot;: &quot;Disallowed Steps&quot;, &quot;description&quot;: &quot;Steps that are not allowed to be run, and will be skipped if attempted&quot;, &quot;default&quot;: [], &quot;type&quot;: &quot;array&quot;, &quot;items&quot;: {&quot;type&quot;: &quot;string&quot;}}' required={false} default="[]"/><ClassPropertyRef name='allow_anonymous_telemetry' details='{&quot;title&quot;: &quot;Allow Anonymous Telemetry&quot;, &quot;description&quot;: &quot;If this field is set to True, we will collect anonymous telemetry as described in the documentation page on telemetry. If set to False, we will not collect any data.&quot;, &quot;default&quot;: true, &quot;type&quot;: &quot;boolean&quot;}' required={false} default="True"/><ClassPropertyRef name='models' details='{&quot;title&quot;: &quot;Models&quot;, &quot;description&quot;: &quot;Configuration for the models used by Continue. Read more about how to configure models in the documentation.&quot;, &quot;default&quot;: {&quot;default&quot;: {&quot;title&quot;: null, &quot;system_message&quot;: null, &quot;context_length&quot;: 2048, &quot;model&quot;: &quot;gpt-4&quot;, &quot;timeout&quot;: 300, &quot;verify_ssl&quot;: null, &quot;prompt_templates&quot;: {}, &quot;api_key&quot;: null, &quot;llm&quot;: null, &quot;class_name&quot;: &quot;MaybeProxyOpenAI&quot;}, &quot;small&quot;: null, &quot;medium&quot;: {&quot;title&quot;: null, &quot;system_message&quot;: null, &quot;context_length&quot;: 2048, &quot;model&quot;: &quot;gpt-3.5-turbo&quot;, &quot;timeout&quot;: 300, &quot;verify_ssl&quot;: null, &quot;prompt_templates&quot;: {}, &quot;api_key&quot;: null, &quot;llm&quot;: null, &quot;class_name&quot;: &quot;MaybeProxyOpenAI&quot;}, &quot;large&quot;: null, &quot;edit&quot;: null, &quot;chat&quot;: null, &quot;unused&quot;: []}, &quot;allOf&quot;: [{&quot;$ref&quot;: &quot;#/definitions/Models&quot;}]}' required={false} default="{&#x27;default&#x27;: {&#x27;title&#x27;: None, &#x27;system_message&#x27;: None, &#x27;context_length&#x27;: 2048, &#x27;model&#x27;: &#x27;gpt-4&#x27;, &#x27;timeout&#x27;: 300, &#x27;verify_ssl&#x27;: None, &#x27;prompt_templates&#x27;: {}, &#x27;api_key&#x27;: None, &#x27;llm&#x27;: None, &#x27;class_name&#x27;: &#x27;MaybeProxyOpenAI&#x27;}, &#x27;small&#x27;: None, &#x27;medium&#x27;: {&#x27;title&#x27;: None, &#x27;system_message&#x27;: None, &#x27;context_length&#x27;: 2048, &#x27;model&#x27;: &#x27;gpt-3.5-turbo&#x27;, &#x27;timeout&#x27;: 300, &#x27;verify_ssl&#x27;: None, &#x27;prompt_templates&#x27;: {}, &#x27;api_key&#x27;: None, &#x27;llm&#x27;: None, &#x27;class_name&#x27;: &#x27;MaybeProxyOpenAI&#x27;}, &#x27;large&#x27;: None, &#x27;edit&#x27;: None, &#x27;chat&#x27;: None, &#x27;unused&#x27;: []}"/><ClassPropertyRef name='temperature' details='{&quot;title&quot;: &quot;Temperature&quot;, &quot;description&quot;: &quot;The temperature parameter for sampling from the LLM. Higher temperatures will result in more random output, while lower temperatures will result in more predictable output. This value ranges from 0 to 1.&quot;, &quot;default&quot;: 0.5, &quot;type&quot;: &quot;number&quot;}' required={false} default="0.5"/><ClassPropertyRef name='custom_commands' details='{&quot;title&quot;: &quot;Custom Commands&quot;, &quot;description&quot;: &quot;An array of custom commands that allow you to reuse prompts. Each has name, description, and prompt properties. When you enter /&lt;name&gt; in the text input, it will act as a shortcut to the prompt.&quot;, &quot;default&quot;: [{&quot;name&quot;: &quot;test&quot;, &quot;prompt&quot;: &quot;Write a comprehensive set of unit tests for the selected code. It should setup, run tests that check for correctness including important edge cases, and teardown. Ensure that the tests are complete and sophisticated. Give the tests just as chat output, don&#x27;t edit any file.&quot;, &quot;description&quot;: &quot;This is an example custom command. Use /config to edit it and create more&quot;}], &quot;type&quot;: &quot;array&quot;, &quot;items&quot;: {&quot;$ref&quot;: &quot;#/definitions/CustomCommand&quot;}}' required={false} default="[{&#x27;name&#x27;: &#x27;test&#x27;, &#x27;prompt&#x27;: &quot;Write a comprehensive set of unit tests for the selected code. It should setup, run tests that check for correctness including important edge cases, and teardown. Ensure that the tests are complete and sophisticated. Give the tests just as chat output, don&#x27;t edit any file.&quot;, &#x27;description&#x27;: &#x27;This is an example custom command. Use /config to edit it and create more&#x27;}]"/><ClassPropertyRef name='slash_commands' details='{&quot;title&quot;: &quot;Slash Commands&quot;, &quot;description&quot;: &quot;An array of slash commands that let you map custom Steps to a shortcut.&quot;, &quot;default&quot;: [], &quot;type&quot;: &quot;array&quot;, &quot;items&quot;: {&quot;$ref&quot;: &quot;#/definitions/SlashCommand&quot;}}' required={false} default="[]"/><ClassPropertyRef name='on_traceback' details='{&quot;title&quot;: &quot;On Traceback&quot;, &quot;description&quot;: &quot;The step that will be run when a traceback is detected (when you use the shortcut cmd+shift+R)&quot;, &quot;allOf&quot;: [{&quot;$ref&quot;: &quot;#/definitions/Step&quot;}]}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='policy_override' details='{&quot;title&quot;: &quot;Policy Override&quot;, &quot;description&quot;: &quot;A Policy object that can be used to override the default behavior of Continue, for example in order to build custom agents that take multiple steps at a time.&quot;, &quot;allOf&quot;: [{&quot;$ref&quot;: &quot;#/definitions/Policy&quot;}]}' required={false} default=""/><ClassPropertyRef name='context_providers' details='{&quot;title&quot;: &quot;Context Providers&quot;, &quot;description&quot;: &quot;A list of ContextProvider objects that can be used to provide context to the LLM by typing &#x27;@&#x27;. Read more about ContextProviders in the documentation.&quot;, &quot;default&quot;: [], &quot;type&quot;: &quot;array&quot;, &quot;items&quot;: {&quot;$ref&quot;: &quot;#/definitions/ContextProvider&quot;}}' required={false} default="[]"/><ClassPropertyRef name='user_token' details='{&quot;title&quot;: &quot;User Token&quot;, &quot;description&quot;: &quot;An optional token to identify the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='data_server_url' details='{&quot;title&quot;: &quot;Data Server Url&quot;, &quot;description&quot;: &quot;The URL of the server where development data is sent. No data is sent unless a valid user token is provided.&quot;, &quot;default&quot;: &quot;https://us-west1-autodebug.cloudfunctions.net&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="https://us-west1-autodebug.cloudfunctions.net"/><ClassPropertyRef name='disable_summaries' details='{&quot;title&quot;: &quot;Disable Summaries&quot;, &quot;description&quot;: &quot;If set to `True`, Continue will not generate summaries for each Step. This can be useful if you want to save on compute.&quot;, &quot;default&quot;: false, &quot;type&quot;: &quot;boolean&quot;}' required={false} default="False"/>
 
 ### Inherited Properties
 
-- 
cgit v1.2.3-70-g09d2