Clean up clarifying question part

README.md

@@ -1 +1,9 @@
 # gpt-engineer
+
+How to use:
+
+- Install requirements.txt `pip install -r requirements.txt`
+- Copy the example folder `cp example -r my-new-project`
+- Edit the file main_prompt in my-new-project
+- run `python main.py my-new-prompt`
+- Check the results in my-new-project/workspace

example/main_prompt

@@ -0,0 +1,86 @@
+Instructions:
+We are writing a feature computation framework.
+
+It will mainly consist of FeatureBuilder classes.
+
+Each Feature Builder will have the methods:
+- get(key, config, context, cache):  Call feature builder dependencies and then compute the feature. Returns value and hash of value.
+  - key:  tuple of arguments that are used to compute the feature
+  - config:  the configuration for the feature
+  - context:  dataclass that contains dependencies and general configuration (see below)
+  - controller:  object that can be used to get other features (see below)
+  - value:  object that can be pickled
+
+It will have the class attr:
+- deps:  list of FeatureBuilder classes
+- default_config:  function that accepts context and returns a config
+
+The Controller will have the methods:
+- get(feature_builder, key, config):  Check the cache, and decide to call feature builder and then returns the output and timestamp it was computed
+  - feature_builder:  FeatureBuilder class
+  - key:  tuple of arguments that are used to compute the feature
+  - configs:  dict of configs that are used to compute features
+
+and the attributes:
+- context:  dataclass that contains dependencies and general configuration (see below)
+- cache: cache for the features
+
+Where it is unclear, please make assumptions and add a comment in the code about it
+
+Here is an example of Builders we want:
+
+ProductEmbeddingString:  takes product_id, queries the product_db and gets the title as a string
+ProductEmbedding: takes string and returns and embedding
+ProductEmbeddingDB: takes just `merchant` name, uses all product_ids and returns the blob that is a database of embeddings
+ProductEmbeddingSearcher: takes a string, constructs embeddingDB feature (note: all features are cached), embeds the string and searches the db
+LLMProductPrompt:  queries the ProductEmbeddingString, and formats a template that says "get recommendations for {title}"
+LLMSuggestions: Takes product_id, looks up prompts and gets list of suggestions of product descriptions
+LLMLogic: Takes the product_id, gets the LLM suggestions, embeds the suggestions, does a search, and returns a list of product_ids
+
+
+The LLMLogic is the logic_builder in a file such as this one:
+```
+def main(merchant, market):
+    cache = get_feature_cache()
+    interaction_data_db = get_interaction_data_db()
+    product_db = get_product_db()
+    merchant_config = get_merchant_config(merchant)
+
+    context = Context(
+        interaction_data_db=interaction_data_db,
+        product_db=product_db,
+        merchant_config=merchant_config,
+    )
+    
+    product_ids = cache(ProductIds).get(
+        key=(merchant, market),
+        context=context,
+        cache=cache,
+    )
+
+    for logic_builder in merchant_config['logic_builders']:
+        for product_id in product_ids:
+            key = (merchant, market, product_id)
+            p2p_recs = cache(logic_builder).get(key=key, context=context, cache=cache)
+            redis.set(key, p2p_recs)
+```
+
+API to product_db:
+```python
+    async def get_product_attribute_dimensions(
+        self,
+    ) -> dict[AttributeId, Dimension]:
+        pass
+
+    async def get_products(
+        self,
+        attribute_ids: set[AttributeId],
+        product_ids: set[ProductId] | None = None,
+    ) -> dict[ProductId, dict[AttributeId, dict[IngestionDimensionKey, Any]]]:
+        pass
+```
+(note, dimensions are not so important. They related to information that varies by: locale, warehouse, pricelist etc)
+
+---
+You will focus on writing the integration test file test_all.py.
+This file will Mock a lot of the necessary interfaces, run the logic LLMLogic and print the results from it.

identity/clarify

@@ -1,5 +0,0 @@
-You will improve instructions by reading:
-1. ORIGINAL INSTRUCTIONS
-2. CLARIFYING QUESTIONS AND ANSWERS
-
-As output you will give a new version of the original instruction but where the answers to the clarifying questions have been incorporated to make it completely clear.

identity/qa

@@ -1,4 +1,3 @@
-You will read instructions and NOT carry them out, only seek to CLARIFY them.
-You will carry out the steps:
-1. Write a list of super short bullets of areas that are unclear
-2. Ask for only one clarifying questions and wait for a reply
+You will read instructions and not carry them out, only seek to clarify them.
+Specifically you will first summarise a list of super short bullets of areas that need clarification.
+Then you will pick one clarifying question, and wait for an answer from the user.

identity/setup

@@ -10,6 +10,6 @@ Before you finish, double check that all parts of the architecture is present in
 
 File syntax:
 
-```main_file.py
+```file.py
 [ADD YOUR CODE HERE]
 ```

identity/use_qa

@@ -0,0 +1,13 @@
+Please now remember the steps:
+
+First lay out the names of the core classes, functions, methods that will be necessary, As well as a quick comment on their purpose.
+Then output the content of each file, with syntax below.
+(You will start with the "entrypoint" file, then go to the ones that are imported by that file, and so on.)
+Make sure that files contain all imports, types etc. The code should be fully functional. Make sure that code in different files are compatible with each other.
+Before you finish, double check that all parts of the architecture is present in the files.
+
+File syntax:
+
+```main_file.py
+[ADD YOUR CODE HERE]
+```

main.py

@@ -13,30 +13,23 @@ import typer
 app = typer.Typer()
 
 
-
 @app.command()
 def chat(
+    project_path: str = typer.Argument(None, help="path"),
+    run_prefix: str = typer.Option("", help="run prefix"),
     model: str = "gpt-4",
     temperature: float = 0.1,
     max_tokens: int = 4096,
     n: int = 1,
     stream: bool = True,
-    input_path: str = typer.Argument(
-        None, help="input path"
-    ),
-    memory_path: str = typer.Argument(
-        None, help="memory path"
-    ),
-    workspace_path: Optional[str] = typer.Option(
-        None, "--out", "-c", help="Code to file path"
-    ),
 ):
 
-    if memory_path is None:
-        memory_path = pathlib.Path(__file__).parent / 'memory'
+    if project_path is None:
+        project_path = str(pathlib.Path(__file__).parent / "example")
 
-    if input_path is None:
-        input_path = pathlib.Path(__file__).parent / 'input'
+    input_path = project_path
+    memory_path = pathlib.Path(project_path) / "memory"
+    workspace_path = pathlib.Path(project_path) / (run_prefix + "workspace")
 
     ai = AI(
         model=model,
@@ -49,13 +42,12 @@ def chat(
 
     dbs = DBs(
         memory=DB(memory_path),
-        logs=DB(pathlib.Path(memory_path) / 'logs'),
+        logs=DB(pathlib.Path(memory_path) / "logs"),
         input=DB(input_path),
         workspace=DB(workspace_path),
-        identity=DB(pathlib.Path(__file__).parent / 'identity'),
+        identity=DB(pathlib.Path(__file__).parent / "identity"),
     )
 
-    run_prefix= workspace_path.split('/')[-1] + '_' if workspace_path is not None else ''
 
     for step in STEPS:
         messages = step(ai, dbs)

requirements.txt

@@ -0,0 +1,2 @@
+openai
+typer

scripts/rerun_edited_message_logs.py

@@ -0,0 +1,48 @@
+import json
+import os
+import pathlib
+from typing import Optional
+import openai
+from chat_to_files import to_files
+from ai import AI
+from steps import STEPS
+from db import DB, DBs
+import typer
+
+
+app = typer.Typer()
+
+
+@app.command()
+def chat(
+    messages_path: str,
+    out_path: str | None = None,
+    model: str = "gpt-4",
+    temperature: float = 0.1,
+    max_tokens: int = 4096,
+    n: int = 1,
+    stream: bool = True,
+):
+
+
+    ai = AI(
+        model=model, temperature=temperature,
+        max_tokens=max_tokens,
+        n=n,
+        stream=stream,
+        stop=None,
+    )
+
+    with open(messages_path) as f:
+        messages = json.load(f)
+
+    messages = ai.next(messages)
+
+    if out_path:
+        to_files(messages[-1]['content'], out_path)
+        with open(pathlib.Path(out_path) / 'all_output.txt', 'w') as f:
+            json.dump(messages[-1]['content'], f)
+
+
+if __name__ == "__main__":
+    app()

steps.py

@@ -3,6 +3,7 @@ from dataclasses import dataclass
 from typing import Callable
 from ai import AI
 from chat_to_files import to_files
+import json
 
 from db import DBs
 from db import DB
@@ -15,36 +16,44 @@ def setup(ai: AI, dbs: DBs):
     to_files(messages[-1]['content'], dbs.workspace)
     return messages
 
-def run_clarified(ai: AI, dbs: DBs):
-    messages = ai.start(setup_sys_prompt(dbs), dbs.input['main_prompt'])
-    to_files(messages[-1]['content'], DB(str(dbs.workspace.path)+'_clarified'))
-    return messages
-
 def clarify(ai: AI, dbs: DBs):
     messages = [ai.fsystem(dbs.identity['qa'])]
     user = dbs.input['main_prompt']
     while True:
         messages = ai.next(messages, user)
+
+        if messages[-1]['content'].strip().lower() == 'no':
+            break
+
         print()
         user = input('Answer: ')
         if not user or user == 'q':
             break
 
-        user += '\nIs anything else unclear? Please ask more questions until instructions are sufficient to write the code.'
+        user += '\n\nIs anything else unclear? If everything is sufficiently clear to write the code, just answer "no".'
 
-    # TOOD: Stop using clarify prompt. Just append questions and answers to the main prompt.
-    prompt = dbs.identity['clarify']
-    messages = ai.next([ai.fsystem(prompt)] + messages[1:], prompt)
-    dbs.memory['clarified_prompt'] = messages[-1]['content']
+    return messages
+
+def run_clarified(ai: AI, dbs: DBs):
+    # get the messages from previous step
+    messages = json.loads(dbs.logs[clarify.__name__])
+
+    messages = (
+        [
+            ai.fsystem(setup_sys_prompt(dbs)),
+        ] +
+        messages[1:]
+    )
+    messages = ai.next(messages, dbs.identity['use_qa'])
+    to_files(messages[-1]['content'], DB(str(dbs.workspace.path)+'_clarified'))
     return messages
 
 
 # STEPS: List[Callable[[AI, DBs], List]] = [
 STEPS=[
-    setup,
-    # clarify,
-    # run_clarified
-    # to_files,
+    # setup,
+    clarify,
+    run_clarified
     # improve_files,
     # run_tests,
     # ImproveBasedOnHumanComments