initial commit

app.py

@@ -0,0 +1,19 @@
+import gradio as gr
+
+from lib.utils import ask
+
+
+def ask_question(question, history):
+    history = history or []
+    answer = ask(question)
+
+    history.append((question, answer))
+    return history, history
+
+
+demo = gr.Interface(fn=ask_question,
+                    title="Ask Lethain a question",
+                    inputs=["text", "state"],
+                    outputs=["chatbot", "state"], allow_flagging="never")
+
+demo.launch()

data/lethain.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb0c043cb792645b49862c59203c7f5d78fabd2dd91f22cee17cf1dfe53da18
+size 163150654

lib/utils.py

@@ -0,0 +1,80 @@
+import os
+from pathlib import Path
+
+import openai
+import tiktoken
+import pandas as pd
+from openai.embeddings_utils import get_embedding, cosine_similarity
+
+encoding_name = "p50k_base"
+
+encoding = tiktoken.get_encoding(encoding_name)
+
+embedding_model = "text-embedding-ada-002"
+openai.api_key = "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"
+
+# read from current directory
+df = pd.read_pickle(Path(__file__).resolve().parent.__str__() + "/../data/lethain.pkl")
+
+
+def search_reviews(df, query):
+    query_embedding = get_embedding(
+        query,
+        engine="text-embedding-ada-002"
+    )
+    df["similarity"] = df.embeddings.apply(lambda x: cosine_similarity(x, query_embedding))
+
+    results = (
+        df.sort_values("similarity", ascending=False)
+
+    )
+    return results
+
+
+def construct_prompt(question: str, df: pd.DataFrame) -> str:
+    MAX_SECTION_LEN = 500
+    SEPARATOR = "\n* "
+
+    separator_len = len(encoding.encode(SEPARATOR))
+
+    f"Context separator contains {separator_len} tokens"
+
+    """
+    Fetch relevant
+    """
+    result = search_reviews(df, question)
+
+    chosen_sections = []
+    chosen_sections_len = 0
+    chosen_sections_indexes = []
+
+    for section_index, row in result.iterrows():
+        # Add contexts until we run out of space.
+
+        tokens_num = len(encoding.encode(row.content))
+        chosen_sections_len += tokens_num
+        if chosen_sections_len > MAX_SECTION_LEN:
+            break
+
+        chosen_sections.append(SEPARATOR + row.content.replace("\n", " "))
+        chosen_sections_indexes.append(str(section_index))
+
+    # Useful diagnostic information
+    print(f"Selected {len(chosen_sections)} document sections:")
+    print("\n".join(chosen_sections_indexes))
+
+    header = """You name is Will Larson, you are CTO at Calm and a blogger about engineering leadership. Answer the question as truthfully as possible using the provided context, and if the answer is not contained within the text below, say "I don't know."\n\nContext:\n"""
+
+    return header + "".join(chosen_sections) + "\n\n Q: " + question + "\n A:"
+
+
+def ask(question):
+    prompt = construct_prompt(question, df)
+    result = openai.Completion.create(
+        prompt=prompt,
+        temperature=0,
+        max_tokens=300,
+        model="text-davinci-003"
+    )
+
+    return result['choices'][0]['text']

requirements.txt

@@ -0,0 +1,74 @@
+aiofiles==22.1.0
+aiohttp==3.8.3
+aiosignal==1.3.1
+altair==4.2.2
+anyio==3.6.2
+async-timeout==4.0.2
+attrs==22.2.0
+blobfile==2.0.1
+certifi==2022.12.7
+charset-normalizer==2.1.1
+click==8.1.3
+contourpy==1.0.7
+cycler==0.11.0
+entrypoints==0.4
+fastapi==0.89.1
+ffmpy==0.3.0
+filelock==3.9.0
+fonttools==4.38.0
+frozenlist==1.3.3
+fsspec==2023.1.0
+gradio==3.16.2
+h11==0.14.0
+httpcore==0.16.3
+httpx==0.23.3
+idna==3.4
+Jinja2==3.1.2
+joblib==1.2.0
+jsonschema==4.17.3
+kiwisolver==1.4.4
+linkify-it-py==1.0.3
+lxml==4.9.2
+markdown-it-py==2.1.0
+MarkupSafe==2.1.2
+matplotlib==3.6.3
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+multidict==6.0.4
+numpy==1.24.1
+openai==0.26.4
+orjson==3.8.5
+packaging==23.0
+pandas==1.5.3
+Pillow==9.4.0
+plotly==5.13.0
+pycryptodome==3.16.0
+pycryptodomex==3.16.0
+pydantic==1.10.4
+pydub==0.25.1
+pyparsing==3.0.9
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+python-multipart==0.0.5
+pytz==2022.7.1
+PyYAML==6.0
+regex==2022.10.31
+requests==2.28.2
+rfc3986==1.5.0
+scikit-learn==1.2.1
+scipy==1.10.0
+six==1.16.0
+sklearn==0.0.post1
+sniffio==1.3.0
+starlette==0.22.0
+tenacity==8.1.0
+threadpoolctl==3.1.0
+tiktoken==0.1.2
+toolz==0.12.0
+tqdm==4.64.1
+typing_extensions==4.4.0
+uc-micro-py==1.0.1
+urllib3==1.26.14
+uvicorn==0.20.0
+websockets==10.4
+yarl==1.8.2