@@ -44,8 +44,8 @@ class SimpleWayOfThinking:
44
44
task = Information(f " { self .task} " ) # inject information to the LLM
45
45
for i in range (4 ):
46
46
step_nb = i + 1
47
- reflexion = Sentence(" Providing a reflexion about the task." , step_nb)
48
- consequence = Sentence(" Providing the consequence of the reflexion ." , step_nb)
47
+ reflection = Sentence(" Providing a reflection about the task." , step_nb)
48
+ consequence = Sentence(" Providing the consequence of the reflection ." , step_nb)
49
49
evaluate = Sentence(" Evaluating the consequence." , step_nb)
50
50
point_of_view = Sentence(f " Providing a point of view about the task different than { povs} " , step_nb)
51
51
point_of_view_qualification = Word(f " Qualifying the point of view, must choose a word different of: { povs} " , step_nb)
@@ -71,8 +71,8 @@ You are a simple thinker. You have a task to perform.
71
71
Always looking for the best way to perform it.
72
72
73
73
#TASK : f'{self.task}'
74
- #REFLEXION : Providing a reflexion about the task. (Response format: a sentence)
75
- #CONSEQUENCE : Providing the consequence of the reflexion . (Response format: a sentence)
74
+ #REFLEXION : Providing a reflection about the task. (Response format: a sentence)
75
+ #CONSEQUENCE : Providing the consequence of the reflection . (Response format: a sentence)
76
76
#EVALUATE : Evaluating the consequence. (Response format: a sentence)
77
77
#POINT_OF_VIEW : f'Providing a point of view about the task different than {povs}' (Response format: a sentence)
78
78
#IMPORTANT : I need to be more creative!
@@ -125,20 +125,20 @@ We can use ReAct prompting with LLM.
125
125
### ReAct example:
126
126
``` You are in a loop of though.
127
127
Question: Here is the question
128
- Reflexion : Thinking about the question
129
- Observation: Providing observation about the Reflexion
130
- Analysis: Formulating an analysis about your current reflexion
131
- Conclusion: Conclude by a synthesis of the reflexion .
128
+ Reflection : Thinking about the question
129
+ Observation: Providing observation about the Reflection
130
+ Analysis: Formulating an analysis about your current reflection
131
+ Conclusion: Conclude by a synthesis of the reflection .
132
132
133
133
Question: {user_input}
134
- Reflexion :
134
+ Reflection :
135
135
```
136
136
137
- In that case, the LLM will follow the provided steps: ` Reflexion ,Observation,Analysis,Conclusion`
137
+ In that case, the LLM will follow the provided steps: ` Reflection ,Observation,Analysis,Conclusion`
138
138
139
- ` Thinking about the quesion ` is the ** Noesis** of ` Reflexion `
139
+ ` Thinking about the quesion ` is the ** Noesis** of ` Reflection `
140
140
141
- The content * generated* by the LLM corresponding to ` Reflexion ` is the ** Noema** .
141
+ The content * generated* by the LLM corresponding to ` Reflection ` is the ** Noema** .
142
142
143
143
### Noema let you write python code that automagically:
144
144
1 . Build the ReAct prompt
@@ -326,7 +326,7 @@ The `LanguageName` type provide a way to generate `LanguageName` code
326
326
327
327
### Information
328
328
329
- The type Information is useful to insert some context to the LLM at the right time in the reflexion process.
329
+ The type Information is useful to insert some context to the LLM at the right time in the reflection process.
330
330
331
331
| Noema Type | Python Type | Usage |
332
332
| -----------| -----------| -----------|
@@ -379,7 +379,7 @@ print(nb_letter)
379
379
# {'s': 1, 't': 1, 'r': 3, 'a': 1, 'w': 1, 'b': 1, 'e': 1, 'y': 1}
380
380
```
381
381
382
- ### Visualisation
382
+ ### Visualization
383
383
384
384
Enabling reflection visualization with ` write_graph = True ` in the Subject init create a PlantUML and Mermaid diagram respectively in ` diagram.puml ` and ` diagram.mmd `
385
385
0 commit comments