Upload with huggingface_hub

#chat.py#

@@ -0,0 +1,76 @@
+# + tags=["hide_inp"]
+desc = """
+# ChatGPT
+
+"ChatGPT" like examples.  Adapted from
+[LangChain](https://langchain.readthedocs.io/en/latest/modules/memory/examples/chatgpt_clone.html)'s
+version of this [blog post](https://www.engraved.blog/building-a-virtual-machine-inside/).
+"""
+# -
+
+
+import warnings
+from dataclasses import dataclass
+from typing import List, Tuple
+import minichain
+
+# + tags=["hide_inp"]
+warnings.filterwarnings("ignore")
+# -
+
+
+# Generic stateful Memory
+
+MEMORY = 2
+
+@dataclass
+class State:
+    memory: List[Tuple[str, str]]
+    human_input: str = ""
+
+    def push(self, response: str) -> "State":
+        memory = self.memory if len(self.memory) < MEMORY else self.memory[1:]
+        return State(memory + [(self.human_input, response)])
+
+# Chat prompt with memory
+
+class ChatPrompt(minichain.TemplatePrompt):
+    template_file = "chatgpt.pmpt.tpl"
+    def parse(self, out: str, inp: State) -> State:
+        result = out.split("Assistant:")[-1]
+        return inp.push(result)
+
+# class Human(minichain.Prompt):
+#     def parse(self, out: str, inp: State) -> State:
+#         return inp.human_input = out
+    
+
+with minichain.start_chain("chat") as backend:
+    prompt = ChatPrompt(backend.OpenAI())
+    state = State([])
+
+    
+examples = [
+    "I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.",
+    "ls ~",
+    "cd ~",
+    "{Please make a file jokes.txt inside and put some jokes inside}",
+    """echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py && python3 run.py""",
+    """echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py && python3 run.py""",
+    """echo -e "echo 'Hello from Docker" > entrypoint.sh && echo -e "FROM ubuntu:20.04\nCOPY entrypoint.sh entrypoint.sh\nENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image""",
+    "nvidia-smi"
+]
+
+gradio = prompt.to_gradio(fields= ["human_input"],
+                          initial_state= state,
+                          examples=examples,
+                          out_type="json",
+                          description=desc
+)
+if __name__ == "__main__":
+    gradio.launch()
+
+# for i in range(len(fake_human)):
+#     human.chain(prompt)
+
+    

#chatgpt.py#

@@ -0,0 +1,78 @@
+# + tags=["hide_inp"]
+
+desc = """
+# ChatGPT
+
+"ChatGPT" like examples.  Adapted from
+[LangChain](https://langchain.readthedocs.io/en/latest/modules/memory/examples/chatgpt_clone.html)'s
+version of this [blog post](https://www.engraved.blog/building-a-virtual-machine-inside/).
+"""
+# -
+
+import warnings
+from dataclasses import dataclass
+from typing import List, Tuple
+from IPython.display import Markdown, display
+import minichain
+
+# + tags=["hide_inp"]
+warnings.filterwarnings("ignore")
+# -
+
+
+# Generic stateful Memory
+
+MEMORY = 2
+
+@dataclass
+class State:
+    memory: List[Tuple[str, str]]
+    human_input: str = ""
+
+    def push(self, response: str) -> "State":
+        memory = self.memory if len(self.memory) < MEMORY else self.memory[1:]
+        return State(memory + [(self.human_input, response)])
+
+# Chat prompt with memory
+
+class ChatPrompt(minichain.TemplatePrompt):
+    template_file = "chatgpt.pmpt.tpl"
+    def parse(self, out: str, inp: State) -> State:
+        result = out.split("Assistant:")[-1]
+        return inp.push(result)
+
+class Human(minichain.Prompt):
+    def parse(self, out: str, inp: State) -> State:
+        return inp.human_input = out
+    
+    
+fake_human = [
+    "I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.",
+    "ls ~",
+    "cd ~",
+    "{Please make a file jokes.txt inside and put some jokes inside}",
+    """echo -e "x=lambda y:y*5+3;print('Result:' + str(x(6)))" > run.py && python3 run.py""",
+    """echo -e "print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])" > run.py && python3 run.py""",
+    """echo -e "echo 'Hello from Docker" > entrypoint.sh && echo -e "FROM ubuntu:20.04\nCOPY entrypoint.sh entrypoint.sh\nENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image""",
+    "nvidia-smi"
+]
+
+with minichain.start_chain("chatgpt") as backend:
+    prompt = ChatPrompt(backend.OpenAI())
+    human = Human(backend.Mock(fake_human))
+    state = State([])
+    for i in range(len(fake_human)):
+        human.chain(prompt)
+        # display(Markdown(f'**Human:** <span style="color: blue">{t}</span>'))
+        # display(Markdown(f'**Assistant:** {state.memory[-1][1]}'))
+        # display(Markdown(f'--------------'))
+
+
+# + tags=["hide_inp"]
+ChatPrompt().show(State([("human 1", "output 1"), ("human 2", "output 2") ], "cd ~"),
+                    "Text Assistant: Hello")
+# -
+
+# View the run log.
+
+minichain.show_log("chatgpt.log")

#ner.py#

@@ -0,0 +1,71 @@
+# + tags=["hide_inp"]
+
+desc = """
+# NER
+
+Notebook implementation of named entity recognition.
+Adapted from [promptify](https://github.com/promptslab/Promptify/blob/main/promptify/prompts/nlp/templates/ner.jinja).
+"""
+# -
+
+import json
+
+import minichain
+
+# Prompt to extract NER tags as json
+
+class NERPrompt(minichain.TemplatePrompt):
+    template_file = "ner.pmpt.tpl"
+
+    def parse(self, response, inp):
+        return json.loads(response)
+
+# Use NER to ask a simple queston.
+
+class TeamPrompt(minichain.Prompt):
+    def prompt(self, inp):
+        return "Can you describe these basketball teams? " + \
+            " ".join([i["E"] for i in inp if i["T"] =="Team"])
+
+    def parse(self, response, inp):
+        return response
+
+# Run the system.
+
+with minichain.start_chain("ner") as backend:
+    ner_prompt = NERPrompt(backend.OpenAI())
+    team_prompt = TeamPrompt(backend.OpenAI())
+    prompt = ner_prompt.chain(team_prompt)
+    # results = prompt(
+    #     {"text_input": "An NBA playoff pairing a year ago, the 76ers (39-20) meet the Miami Heat (32-29) for the first time this season on Monday night at home.",
+    #      "labels" : ["Team", "Date"],
+    #      "domain": "Sports"
+    #      }
+    # )
+    # print(results)
+
+gradio = prompt.to_gradio(fields =["text_input", "labels", "domain"],
+                          examples=[["An NBA playoff pairing a year ago, the 76ers (39-20) meet the Miami Heat (32-29) for the first time this season on Monday night at home.", "Team, Date", "Sports"]],
+                          description=desc)
+
+    
+if __name__ == "__main__":
+    gradio.launch()
+
+    
+# View prompt examples.
+
+# + tags=["hide_inp"]
+# NERPrompt().show(
+#     {
+#         "input": "I went to New York",
+#         "domain": "Travel",
+#         "labels": ["City"]
+#     },
+#     '[{"T": "City", "E": "New York"}]',
+# )
+# # -
+
+# # View log.
+
+# minichain.show_log("ner.log")

#qa.py#

@@ -1,10 +1,14 @@
-# # QA
+# + tags=["hide_inp"]
+desc = """
+# QA
 
-# Questions answering with embeddings.  Adapted from [OpenAI
-# Notebook](https://github.com/openai/openai-cookbook/blob/main/examples/Question_answering_using_embeddings.ipynb).
+Questions answering with embeddings.  Adapted from [OpenAI Notebook](https://github.com/openai/openai-cookbook/blob/main/examples/Question_answering_using_embeddings.ipynb).
+"""
+# -
 
 import datasets
 import numpy as np
+
 from minichain import EmbeddingPrompt, TemplatePrompt, show_log, start_chain
 
 # We use Hugging Face Datasets as the database by assigning
@@ -31,15 +35,22 @@ class QAPrompt(TemplatePrompt):
 
 
 with start_chain("qa") as backend:
-    question = "Who won the 2020 Summer Olympics men's high jump?"
     prompt = KNNPrompt(backend.OpenAIEmbed()).chain(QAPrompt(backend.OpenAI()))
-    result = prompt(question)
-    print(result)
+    
+question = "Who won the 2020 Summer Olympics men's high jump?"
 
-# + tags=["hide_inp"]
-QAPrompt().show(
-    {"question": "Who won the race?", "docs": ["doc1", "doc2", "doc3"]}, "Joe Bob"
-)
-# -
+gradio = prompt.to_gradio(fields=["query"],
+                          examples=[question],
+                          description=desc)
+if __name__ == "__main__":
+    gradio.launch()
+
+
+
+# # + tags=["hide_inp"]
+# QAPrompt().show(
+#     {"question": "Who won the race?", "docs": ["doc1", "doc2", "doc3"]}, "Joe Bob"
+# )
+# # -
 
-show_log("qa.log")
+# show_log("qa.log")

app.py

@@ -13,9 +13,9 @@ css = "#clean div.form {border: 0px} #response {border: 0px; background: #ffeec6
 with gr.Blocks(css=css) as demo:
     gr.HTML("<center> <img width='10%' style='display:inline; padding: 5px' src='https://user-images.githubusercontent.com/35882/218286642-67985b6f-d483-49be-825b-f62b72c469cd.png'> <h1 style='display:inline'> Mini-Chain </h1> <img width='10%' style='display:inline;padding: 5px' src='https://avatars.githubusercontent.com/u/25720743?s=200&v=4'> </center><br><center><a href='https://github.com/srush/minichain'>[code]</a>  <a href='https://user-images.githubusercontent.com/35882/218286642-67985b6f-d483-49be-825b-f62b72c469cd.png'>[docs]</a></center>")
 
-    gr.TabbedInterface([chat, qa, gatsby,  math_demo, ner,  bash, pal, stats],
-                       ["Chat",  "QA", "Book",  "Math", "NER", "Bash", "PAL", "Stats"],
-                       css= css)
+    gr.TabbedInterface([math_demo, qa,  chat, gatsby,  ner, bash, pal, stats],
+                       ["Math", "QA", "Chat", "Book", "NER", "Bash", "PAL", "Stats"],
+                       css = css)
 
 demo.launch()
 

bash.py

@@ -1,6 +1,12 @@
-# Notebook to generate and run a bash command.
-# Adapted from LangChain
-# [BashChain](https://langchain.readthedocs.io/en/latest/modules/chains/examples/llm_bash.html)
+# + tags=["hide_inp"]
+
+desc = """
+# Bash 
+
+Notebook to generate and run a bash command. Adapted from LangChain
+[BashChain](https://langchain.readthedocs.io/en/latest/modules/chains/examples/llm_bash.html)
+"""
+# -
 
 import minichain
 
@@ -38,9 +44,9 @@ with minichain.start_chain("bash") as backend:
 gradio = prompt.to_gradio(fields =["question"],
                  examples=['Go up one directory, and then into the minichain directory,'
                            'and list the files in the directory'],
-                 out_type="markdown"
-                 
-)
+                          out_type="markdown",
+                          description=desc)                 
+
 if __name__ == "__main__":
     gradio.launch()
 

chat.py

@@ -1,3 +1,13 @@
+# + tags=["hide_inp"]
+
+desc = """
+# ChatGPT
+
+"ChatGPT" like examples.  Adapted from
+[LangChain](https://langchain.readthedocs.io/en/latest/modules/memory/examples/chatgpt_clone.html)'s
+version of this [blog post](https://www.engraved.blog/building-a-virtual-machine-inside/).
+"""
+# -
 
 
 import warnings
@@ -55,7 +65,8 @@ examples = [
 gradio = prompt.to_gradio(fields= ["human_input"],
                           initial_state= state,
                           examples=examples,
-                          out_type="json"
+                          out_type="json",
+                          description=desc
 )
 if __name__ == "__main__":
     gradio.launch()

gatsby.py

@@ -1,6 +1,11 @@
-# Questions answering with Hugging Face embeddings.  Adapted from the
-# [LlamaIndex
-# example](https://github.com/jerryjliu/gpt_index/blob/main/examples/gatsby/TestGatsby.ipynb).
+# + tags=["hide_inp"]
+desc = """
+# Book QA
+
+Questions answering with Hugging Face embeddings.  Adapted from the [LlamaIndex
+ example](https://github.com/jerryjliu/gpt_index/blob/main/examples/gatsby/TestGatsby.ipynb).
+"""
+# -
 
 import datasets
 import numpy as np
@@ -40,7 +45,8 @@ with start_chain("gatsby") as backend:
 
 gradio = prompt.to_gradio(fields=["query"],
                           examples=["What did Gatsby do before he met Daisy?"],
-                          keys={"HF_KEY"})
+                          keys={"HF_KEY"},
+                          description=desc)
 if __name__ == "__main__":
     gradio.launch()
 

math_demo.py

@@ -1,5 +1,11 @@
-# Notebook to answer a math problem with code.
-# Adapted from Dust [maths-generate-code](https://dust.tt/spolu/a/d12ac33169)
+# + tags=["hide_inp"]
+desc = """
+# Math
+
+Notebook to answer a math problem with code.
+Adapted from Dust [maths-generate-code](https://dust.tt/spolu/a/d12ac33169)
+"""
+# -
 
 import minichain
 
@@ -19,8 +25,9 @@ with minichain.start_chain("math") as backend:
     # print(result)
 
 gradio = prompt.to_gradio(fields =["question"],
-                 examples=["What is the sum of the powers of 3 (3^i) that are smaller than 100?"],
-                 out_type="markdown"
+                          examples=["What is the sum of the powers of 3 (3^i) that are smaller than 100?"],
+                          out_type="markdown",
+                          description=desc
                  
 )
 if __name__ == "__main__":

ner.py

@@ -1,7 +1,12 @@
-# # NER
+# + tags=["hide_inp"]
+
+desc = """
+# NER
 
-# Notebook implementation of named entity recognition.
-# Adapted from [promptify](https://github.com/promptslab/Promptify/blob/main/promptify/prompts/nlp/templates/ner.jinja).
+Notebook implementation of named entity recognition.
+Adapted from [promptify](https://github.com/promptslab/Promptify/blob/main/promptify/prompts/nlp/templates/ner.jinja).
+"""
+# -
 
 import json
 
@@ -40,7 +45,8 @@ with minichain.start_chain("ner") as backend:
     # print(results)
 
 gradio = prompt.to_gradio(fields =["text_input", "labels", "domain"],
-                 examples=[["An NBA playoff pairing a year ago, the 76ers (39-20) meet the Miami Heat (32-29) for the first time this season on Monday night at home.", "Team, Date", "Sports"]])
+                          examples=[["An NBA playoff pairing a year ago, the 76ers (39-20) meet the Miami Heat (32-29) for the first time this season on Monday night at home.", "Team, Date", "Sports"]],
+                          description=desc)
 
     
 if __name__ == "__main__":

pal.py

@@ -1,4 +1,8 @@
-# Adapted from Prompt-aided Language Models [PAL](https://arxiv.org/pdf/2211.10435.pdf).
+desc = """
+# PAL
+
+Adapted from Prompt-aided Language Models [PAL](https://arxiv.org/pdf/2211.10435.pdf).
+"""
 
 import minichain
 
@@ -28,7 +32,8 @@ question = "Melanie is a door-to-door saleswoman. She sold a third of her " \
     "how many did she start with?"
     
 gradio = prompt.to_gradio(fields =["question"],
-                 examples=[question])
+                          examples=[question],
+                          description=desc)
 if __name__ == "__main__":
     gradio.launch()
 

qa.py

@@ -1,7 +1,10 @@
-# # QA
+# + tags=["hide_inp"]
+desc = """
+# QA
 
-# Questions answering with embeddings.  Adapted from [OpenAI
-# Notebook](https://github.com/openai/openai-cookbook/blob/main/examples/Question_answering_using_embeddings.ipynb).
+Questions answering with embeddings.  Adapted from [OpenAI Notebook](https://github.com/openai/openai-cookbook/blob/main/examples/Question_answering_using_embeddings.ipynb).
+"""
+# -
 
 import datasets
 import numpy as np
@@ -37,7 +40,8 @@ with start_chain("qa") as backend:
 question = "Who won the 2020 Summer Olympics men's high jump?"
 
 gradio = prompt.to_gradio(fields=["query"],
-                          examples=[question])
+                          examples=[question],
+                          description=desc)
 if __name__ == "__main__":
     gradio.launch()
 

stats.py

@@ -1,4 +1,9 @@
-# Information extraction from a typed data specification.
+
+desc = """
+# Typed Extraction
+
+Information extraction from a typed data specification.
+"""
 
 import minichain
 from dataclasses import dataclass
@@ -40,8 +45,9 @@ with minichain.start_chain("stats") as backend:
 
 article = open("sixers.txt").read()
 gradio = prompt.to_gradio(fields =["passage"],
-                 examples=[article],
-                 out_type="json"
+                          examples=[article],
+                          out_type="json",
+                          desc
 )
 if __name__ == "__main__":
     gradio.launch()