change configs for new litellm backend

CF_Code.yaml

@@ -17,20 +17,23 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
 
-generation_parameters:
+backend:
+  __target__: flows.backends.llm_lite.LiteLLMBackend
+  api_infos: ${local.api_information}
+  wait_time_per_key: 6
+  model_name:
+    openai: "gpt-4"
+    azure: "azure/gpt-4"
   n: 1
   max_tokens: 3000
   temperature: 0.3
-
-  model_kwargs:
-    top_p: 0.2
-    frequency_penalty: 0
-    presence_penalty: 0
+  top_p: 0.2
+  frequency_penalty: 0
+  presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     Your goal is to provide executable Python code that solves a competitive programming problem. The code should correctly handle all corner cases in order to pass the hidden test cases, which are used to evaluate the correctness of the solution.
 
@@ -43,17 +46,17 @@ system_message_prompt_template:
 
     The user will provide you with a task and an output format that you will strictly follow.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -79,4 +82,4 @@ init_human_message_prompt_template:
     - "io_examples_and_explanation"
   partial_variables:
     code_placeholder: "{{python_code}}"
-  template_format: jinja2
+  

CF_CodeCollab.yaml

@@ -18,7 +18,7 @@ subflows_config:
     _target_: .CF_Code.instantiate_from_default_config
     name: "CodeGenerator"
     human_message_prompt_template:
-      _target_: langchain.PromptTemplate
+      _target_: flows.prompt_template.JinjaPrompt
       template: |2-
         # Feedback on the last proposed solution
         {{code_feedback}}

CF_CodeCritic.yaml

@@ -18,20 +18,22 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
-
-generation_parameters:
+backend:
+  __target__: flows.backends.llm_lite.LiteLLMBackend
+  api_infos: ${local.api_information}
+  model_name:
+      openai: "gpt-4"
+      azure: "azure/gpt-4"
   n: 1
   max_tokens: 3000
   temperature: 0.3
 
-  model_kwargs:
-    top_p: 0.2
-    frequency_penalty: 0
-    presence_penalty: 0
+  top_p: 0.2
+  frequency_penalty: 0
+  presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     Your goal is to identify potential issues with a competitive programming solution attempt.
 
@@ -46,17 +48,17 @@ system_message_prompt_template:
     Crucially, your goal is to correctly identify potential issues with the solution attempt, and not to provide the code implementation yourself.
     The user will provide you with a task and an output format that you will strictly follow.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -82,4 +84,4 @@ init_human_message_prompt_template:
     - "output_description"
     - "io_examples_and_explanation"
     - "code"
-  template_format: jinja2
+  

CF_CodeCriticWrongAttempt.yaml

@@ -19,20 +19,23 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
-
-generation_parameters:
+backend:
+  __target__: flows.backends.llm_lite.LiteLLMBackend
+  api_infos: ${local.api_information}
+  model_name:
+    openai: "gpt-4"
+    azure: "azure/gpt-4"
   n: 1
   max_tokens: 3000
   temperature: 0.3
 
-  model_kwargs:
-    top_p: 0.2
-    frequency_penalty: 0
-    presence_penalty: 0
+
+  top_p: 0.2
+  frequency_penalty: 0
+  presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     Your goal is to identify the issues with an incorrect competitive programming solution attempt.
   
@@ -48,17 +51,17 @@ system_message_prompt_template:
     Some aspects to consider: Is the input correctly parsed? Is the output correctly formatted? Are the corner cases correctly handled? Is there a logical mistake with the algorithm itself?
     Use the code execution results provided in the issue description to guide your reasoning/debugging.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -87,4 +90,4 @@ init_human_message_prompt_template:
     - "io_examples_and_explanation"
     - "code"
     - "testing_results_summary"
-  template_format: jinja2
+  

CF_CodeCriticWrongAttemptWithPlan.yaml

@@ -20,20 +20,23 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
-
-generation_parameters:
+backend:
+  __target__: flows.backends.llm_lite.LiteLLMBackend
+  api_infos: ${local.api_information}
+  model_name:
+      openai: "gpt-4"
+      azure: "azure/gpt-4"
   n: 1
   max_tokens: 3000
   temperature: 0.3
 
-  model_kwargs:
-    top_p: 0.2
-    frequency_penalty: 0
-    presence_penalty: 0
+  
+  top_p: 0.2
+  frequency_penalty: 0
+  presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     Your goal is to identify the issues with an incorrect competitive programming solution attempt.
 
@@ -51,17 +54,17 @@ system_message_prompt_template:
     Some aspects to consider: Is the input correctly parsed? Is the output correctly formatted? Is the code implementation consistent with the conceptual solution? Are the corner cases correctly handled? Is there a logical mistake with the algorithm itself?
     Use the code execution results provided in the issue description to guide your reasoning/debugging.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -94,4 +97,4 @@ init_human_message_prompt_template:
     - "plan"
     - "code"
     - "testing_results_summary"
-  template_format: jinja2
+  

CF_CodeDebug.yaml

@@ -22,7 +22,12 @@ subflows_config:
   CodeGenerator:
     _target_: .CF_Code.instantiate_from_default_config
     name: "CodeGenerator"
-    model_name: "gpt-4"
+    backend:
+      __target__: flows.backends.llm_lite.LiteLLMBackend
+      api_infos: ${local.api_information}
+      model_name:
+        openai: "gpt-4"
+        azure: "azure/gpt-4"
     human_message_prompt_template:
       template: |2-
         {{testing_results_summary}}

CF_CodeDebugCollab.yaml

@@ -21,9 +21,14 @@ subflows_config:
   CodeGenerator:
     _target_: .CF_Code.instantiate_from_default_config
     name: "CodeGenerator"
-    model_name: "gpt-4"
+    backend:
+      __target__: flows.backends.llm_lite.LiteLLMBackend
+      api_infos: ${local.api_information}
+      model_name:
+        openai: "gpt-4"
+        azure: "azure/gpt-4"
     human_message_prompt_template:
-      _target_: langchain.PromptTemplate
+      _target_: flows.prompt_template.JinjaPrompt
       template: |2-
         {{testing_results_summary}}
       

CF_CodeDebugCollabWithPlan.yaml

@@ -22,9 +22,14 @@ subflows_config:
   CodeGenerator:
     _target_: .CF_CodeWithPlan.instantiate_from_default_config
     name: "CodeGenerator"
-    model_name: "gpt-4"
+    backend:
+      __target__: flows.backends.llm_lite.LiteLLMBackend
+      api_infos: ${local.api_information}
+      model_name:
+        openai: "gpt-4"
+        azure: "azure/gpt-4"
     human_message_prompt_template:
-      _target_: langchain.PromptTemplate
+      _target_: flows.prompt_template.JinjaPrompt
       template: |2-
         {{testing_results_summary}}
       

CF_CodeWithPlan.yaml

@@ -18,20 +18,21 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
-
-generation_parameters:
+backend:
+  __target__: flows.backends.llm_lite.LiteLLMBackend
+  api_infos: ${local.api_information}
+  model_name:
+    openai: "gpt-4"
+    azure: "azure/gpt-4"
   n: 1
   max_tokens: 3000
   temperature: 0.3
-
-  model_kwargs:
-    top_p: 0.2
-    frequency_penalty: 0
-    presence_penalty: 0
+  top_p: 0.2
+  frequency_penalty: 0
+  presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     Your goal is to provide executable Python code that solves a competitive programming problem. The code should correctly handle all corner cases in order to pass the hidden test cases, which are used to evaluate the correctness of the solution.
 
@@ -46,17 +47,17 @@ system_message_prompt_template:
 
     The user will provide you with a task and an output format that you will strictly follow.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -86,4 +87,4 @@ init_human_message_prompt_template:
     - "plan"
   partial_variables:
     code_placeholder: "{{python_code}}"
-  template_format: jinja2
+  

CF_Plan.yaml

@@ -17,19 +17,19 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
-generation_parameters:
+model_name:
+    openai: "gpt-4"
+    azure: "azure/gpt-4"
   n: 1
   max_tokens: 3000
   temperature: 0.3
 
-  model_kwargs:
-    top_p: 0.2
-    frequency_penalty: 0
-    presence_penalty: 0
+  top_p: 0.2
+  frequency_penalty: 0
+  presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     Your goal is to provide a high-level conceptual solution that, if implemented, will solve a given competitive programming problem.
 
@@ -44,17 +44,17 @@ system_message_prompt_template:
 
     The user will provide you with a task and an output format that you will strictly follow.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -79,4 +79,4 @@ init_human_message_prompt_template:
     - "io_examples_and_explanation"
   partial_variables:
     plan_placeholder: "{{conceptual_solution}}"
-  template_format: jinja2
+  

CF_PlanCollab.yaml

@@ -21,7 +21,7 @@ subflows_config:
   PlanGenerator:
     _target_: .CF_Plan.instantiate_from_default_config
     human_message_prompt_template:
-      _target_: langchain.PromptTemplate
+      _target_: flows.prompt_template.JinjaPrompt
       template: |2-
         # Feedback on the last proposed conceptual solution
         {{plan_feedback}}
@@ -36,7 +36,7 @@ subflows_config:
         - plan_feedback
       partial_variables:
         plan_placeholder: "{{conceptual_solution}}"
-      template_format: jinja2
+      
     input_interface_initialized:
       - "plan_feedback"
   PlanCritic:

CF_PlanCritic.yaml

@@ -18,20 +18,22 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
-
-generation_parameters:
+backend:
+  __target__: flows.backends.llm_lite.LiteLLMBackend
+  api_infos: ${local.api_information}
+  model_name:
+    openai: "gpt-4"
+    azure: "azure/gpt-4"
   n: 1
   max_tokens: 3000
   temperature: 0.3
 
-  model_kwargs:
-    top_p: 0.2
-    frequency_penalty: 0
-    presence_penalty: 0
+  top_p: 0.2
+  frequency_penalty: 0
+  presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
       Your goal is to identify potential issues with a conceptual solution to a given competitive programming problem.
 
@@ -47,17 +49,17 @@ system_message_prompt_template:
       Some aspects to consider: Are there any logical mistakes with the proposed algorithm? Are the corner cases correctly handled?
       The user will provide you with a task and an output format that you will strictly follow.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -81,4 +83,4 @@ init_human_message_prompt_template:
     - "output_description"
     - "io_examples_and_explanation"
     - "plan"
-  template_format: jinja2
+  

LC_Code.yaml

@@ -17,20 +17,23 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
+backend:
+  __target__: flows.backends.llm_lite.LiteLLMBackend
+  api_infos: ${local.api_information}
+  model_name:
+    openai: "gpt-4"
+    azure: "azure/gpt-4"
 
-generation_parameters:
   n: 1
   max_tokens: 3000
   temperature: 0.3
 
-  model_kwargs:
-    top_p: 0.2
-    frequency_penalty: 0
-    presence_penalty: 0
+  top_p: 0.2
+  frequency_penalty: 0
+  presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     Your goal is to provide executable Python code that solves a coding interview problem. The code should correctly handle all corner cases in order to pass the hidden test cases, which are used to evaluate the correctness of the solution.
 
@@ -41,17 +44,17 @@ system_message_prompt_template:
 
     The user will provide you with a task and an output format that you will strictly follow.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -78,4 +81,4 @@ init_human_message_prompt_template:
     - "python_stub"
   partial_variables:
     code_placeholder: "{{python_code}}"
-  template_format: jinja2
+  

LC_CodeCollab.yaml

@@ -18,7 +18,7 @@ subflows_config:
     _target_: .LC_Code.instantiate_from_default_config
     name: "CodeGenerator"
     human_message_prompt_template:
-      _target_: langchain.PromptTemplate
+      _target_: flows.prompt_template.JinjaPrompt
       template: |2-
         # Feedback on the last proposed solution
         {{code_feedback}}

LC_CodeCritic.yaml

@@ -18,20 +18,24 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
+backend:
+  __target__: flows.backends.llm_lite.LiteLLMBackend
+  api_infos: ${local.api_information}
+  model_name:
+    openai: "gpt-4"
+    azure: "azure/gpt-4"
+
 
-generation_parameters:
   n: 1
   max_tokens: 3000
   temperature: 0.3
 
-  model_kwargs:
-    top_p: 0.2
-    frequency_penalty: 0
-    presence_penalty: 0
+  top_p: 0.2
+  frequency_penalty: 0
+  presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     Your goal is to identify potential issues with a competitive programming solution attempt.
 
@@ -45,17 +49,17 @@ system_message_prompt_template:
     Crucially, your goal is to correctly identify potential issues with the solution attempt, and not to provide the code implementation yourself.
     The user will provide you with a task and an output format that you will strictly follow.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -83,4 +87,4 @@ init_human_message_prompt_template:
     - "constraints"
     - "python_stub"
     - "code"
-  template_format: jinja2
+  

LC_CodeCriticWrongAttempt.yaml

@@ -19,20 +19,23 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
+backend:
+  __target__: flows.backends.llm_lite.LiteLLMBackend
+  api_infos: ${local.api_information}
+  model_name:
+    openai: "gpt-4"
+    azure: "azure/gpt-4"
 
-generation_parameters:
   n: 1
   max_tokens: 3000
   temperature: 0.3
 
-  model_kwargs:
-    top_p: 0.2
-    frequency_penalty: 0
-    presence_penalty: 0
+  top_p: 0.2
+  frequency_penalty: 0
+  presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     Your goal is to identify the issues with an incorrect competitive programming solution attempt.
   
@@ -47,17 +50,17 @@ system_message_prompt_template:
     Some aspects to consider: Is the input correctly parsed? Is the output correctly formatted? Are the corner cases correctly handled? Is there a logical mistake with the algorithm itself?
     Use the code execution results provided in the issue description to guide your reasoning/debugging.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -88,4 +91,4 @@ init_human_message_prompt_template:
     - "python_stub"
     - "code"
     - "testing_results_summary"
-  template_format: jinja2
+  

LC_CodeDebug.yaml

@@ -22,7 +22,12 @@ subflows_config:
   CodeGenerator:
     _target_: .LC_Code.instantiate_from_default_config
     name: "CodeGenerator"
-    model_name: "gpt-4"
+    backend:
+      __target__: flows.backends.llm_lite.LiteLLMBackend
+      api_infos: ${local.api_information}
+      model_name:
+        openai: "gpt-4"
+        azure: "azure/gpt-4"
     human_message_prompt_template:
       template: |2-
         {{testing_results_summary}}

LC_CodeDebugCollab.yaml

@@ -21,9 +21,14 @@ subflows_config:
   CodeGenerator:
     _target_: .LC_Code.instantiate_from_default_config
     name: "CodeGenerator"
-    model_name: "gpt-4"
+    backend:
+      __target__: flows.backends.llm_lite.LiteLLMBackend
+      api_infos: ${local.api_information}
+      model_name:
+        openai: "gpt-4"
+        azure: "azure/gpt-4"
     human_message_prompt_template:
-      _target_: langchain.PromptTemplate
+      _target_: flows.prompt_template.JinjaPrompt
       template: |2-
         {{testing_results_summary}}
       

LC_CodeWithPlan.yaml

@@ -18,7 +18,12 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
+backend:
+  __target__: flows.backends.llm_lite.LiteLLMBackend
+  api_infos: ${local.api_information}
+  model_name:
+    openai: "gpt-4"
+    azure: "azure/gpt-4"
 
 generation_parameters:
   n: 1
@@ -31,7 +36,7 @@ generation_parameters:
     presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     Your goal is to provide executable Python code that solves a coding interview problem. The code should correctly handle all corner cases in order to pass the hidden test cases, which are used to evaluate the correctness of the solution.
 
@@ -44,17 +49,17 @@ system_message_prompt_template:
 
     The user will provide you with a task and an output format that you will strictly follow.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -87,4 +92,4 @@ init_human_message_prompt_template:
     - "plan"
   partial_variables:
     code_placeholder: "{{python_code}}"
-  template_format: jinja2
+  

LC_Plan.yaml

@@ -16,19 +16,20 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
-generation_parameters:
+model_name:
+  openai: "gpt-4"
+  azure: "azure/gpt-4"
+
   n: 1
   max_tokens: 3000
   temperature: 0.3
 
-  model_kwargs:
-    top_p: 0.2
-    frequency_penalty: 0
-    presence_penalty: 0
+  top_p: 0.2
+  frequency_penalty: 0
+  presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     Your goal is to provide a high-level conceptual solution that, if implemented, will solve a given coding interview problem.
 
@@ -41,17 +42,17 @@ system_message_prompt_template:
 
     The user will provide you with a task and an output format that you will strictly follow.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -72,5 +73,5 @@ init_human_message_prompt_template:
     - "constraints"
   partial_variables:
     plan_placeholder: "{{conceptual_solution}}"
-  template_format: jinja2
+  
 

LC_PlanCollab.yaml

@@ -21,7 +21,7 @@ subflows_config:
   PlanGenerator:
     _target_: .LC_Plan.instantiate_from_default_config
     human_message_prompt_template:
-      _target_: langchain.PromptTemplate
+      _target_: flows.prompt_template.JinjaPrompt
       template: |2-
         # Feedback on the last proposed conceptual solution
         {{plan_feedback}}
@@ -36,7 +36,7 @@ subflows_config:
         - plan_feedback
       partial_variables:
         plan_placeholder: "{{conceptual_solution}}"
-      template_format: jinja2
+      
     input_interface_initialized:
       - "plan_feedback"
   PlanCritic:

LC_PlanCritic.yaml

@@ -18,20 +18,21 @@ output_interface:
   - "api_output"
 
 # ~~~ Flow specification ~~~
-model_name: "gpt-4"
+model_name:
+    openai: "gpt-4"
+    azure: "azure/gpt-4"
 
-generation_parameters:
   n: 1
   max_tokens: 3000
   temperature: 0.3
 
-  model_kwargs:
-    top_p: 0.2
-    frequency_penalty: 0
-    presence_penalty: 0
+ 
+  top_p: 0.2
+  frequency_penalty: 0
+  presence_penalty: 0
 
 system_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
       Your goal is to identify potential issues with a conceptual solution to a given competitive programming problem.
 
@@ -45,17 +46,17 @@ system_message_prompt_template:
       Some aspects to consider: Are there any logical mistakes with the proposed algorithm? Are the corner cases correctly handled?
       The user will provide you with a task and an output format that you will strictly follow.
   input_variables: []
-  template_format: jinja2
+  
 
 human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: "{{query}}"
   input_variables:
     - "query"
-  template_format: jinja2
+  
 
 init_human_message_prompt_template:
-  _target_: langchain.PromptTemplate
+  _target_: flows.prompt_template.JinjaPrompt
   template: |2-
     # Problem statement
     {{problem_description}}
@@ -81,4 +82,4 @@ init_human_message_prompt_template:
     - "constraints"
     - "python_stub"
     - "plan"
-  template_format: jinja2
+  

__init__.py

@@ -1,6 +1,6 @@
 # ~~~ Specify the dependencies ~~~
 dependencies = [
-    {"url": "aiflows/OpenAIChatFlowModule", "revision": "6a1e351a915f00193f18f3da3b61c497df1d31a3"},
+    {"url": "aiflows/OpenAIChatFlowModule", "revision": "821d1ba993c0be5af1b17c4e47e7dd72c4e6fd9e"},
     {"url": "aiflows/FixedReplyFlowModule", "revision": "65fbdbe19f5a8fdc48810810812552c5674d35a5"},
 ]