initial updates

app.py

@@ -1,11 +1,83 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from sentence_transformers import SentenceTransformer, util
+import torch
+import pandas as pd
+
+def load_bible():
+    # Replace: 1=Genesis, 2=Exodus, ... 66=Revelation
+    books = ['Genesis', 'Exodus', 'Leviticus', 'Numbers', 'Deuteronomy',
+           'Joshua', 'Judges', 'Ruth', '1 Samuel', '2 Samuel', '1 Kings',
+           '2 Kings', '1 Chronicles', '2 Chronicles', 'Ezra', 'Nehemiah',
+           'Esther', 'Job', 'Psalms', 'Proverbs', 'Ecclesiastes',
+           'Song of Solomon', 'Isaiah', 'Jeremiah', 'Lamentations', 'Ezekiel',
+           'Daniel', 'Hosea', 'Joel', 'Amos', 'Obadiah', 'Jonah', 'Micah',
+           'Nahum', 'Habakkuk', 'Zephaniah', 'Haggai', 'Zechariah', 'Malachi',
+           'Matthew', 'Mark', 'Luke', 'John', 'Acts', 'Romans',
+           '1 Corinthians', '2 Corinthians', 'Galatians', 'Ephesians',
+           'Philippians', 'Colossians', '1 Thessalonians', '2 Thessalonians',
+           '1 Timothy', '2 Timothy', 'Titus', 'Philemon', 'Hebrews', 'James',
+           '1 Peter', '2 Peter', '1 John', '2 John', '3 John', 'Jude',
+           'Revelation']
+    lookup = {}
+    for i, j in enumerate(books):
+        lookup[i+1]=j
+    lookup
+
+    esv = pd.read_csv('t_esv.csv').\
+        rename(columns = {"b":"book"}).drop(["id"], axis=1)
+    esv.book = esv.book.replace(lookup)
+    return esv
+
+def load_embeddings(fn):
+    with open(fn, "rb") as f:
+        embeddings = torch.load(f)
+    return embeddings
+
+def search(searchText, k = 5, show_html=False, return_str=False):
+    emb = model.encode(searchText, convert_to_tensor=True)
+    cos_scores = util.cos_sim(emb, embeddings)[0]
+    top_results = torch.topk(cos_scores, k = k)
+
+    x = bible.iloc[top_results.indices.cpu().detach().numpy(), :]
+
+    if show_html:
+        for index, row in x.iterrows():
+            display(HTML(f'<p style="font-size: 22px;"><strong>{row.book} {row.c}:{row.v}</strong>  <em>{row.t}</em></p><br>'))
+
+    if return_str:
+        s = []
+        for index, row in x.iterrows():
+            tmp = f"({row.book} {row.c}:{row.v}) {row.t}"
+            s.append(tmp)
+
+        return "\n".join(s)
+
+    else:
+        return x
+
+
+def create_prompt(q):
+    ctx = search(q, k=10, return_str = True)
+    s = f"""Context:
+    {ctx}
+    Question:
+    {q}
+    """
+    
+    return s
+
+# Constants
+model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
+embeddings = load_embeddings("esv_embeddings.pt")
+bible = load_bible()
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# client = InferenceClient("microsoft/Phi-3-mini-4k-instruct")
 
 def respond(
     message,
@@ -23,10 +95,11 @@ def respond(
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
 
+    message = create_prompt(message)
     messages.append({"role": "user", "content": message})
 
     response = ""
-
+    
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -45,7 +118,7 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a Christian Pastor. Provide spiritual wisdom, based on biblical truth found in the context. Quote from the context when appropriate.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(

esv_embeddings.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97bdae9e2437f18a0078258bee489478b3dfb73f7164365af696055746c79c0d
+size 47772316

requirements.txt

@@ -1 +1,91 @@
-huggingface_hub==0.22.2
+aiofiles==23.2.1
+altair==5.3.0
+annotated-types==0.7.0
+anyio==4.4.0
+attrs==23.2.0
+certifi==2024.7.4
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.1
+cycler==0.12.1
+dnspython==2.6.1
+email_validator==2.2.0
+fastapi==0.111.0
+fastapi-cli==0.0.4
+ffmpy==0.3.2
+filelock==3.15.4
+fonttools==4.53.1
+fsspec==2024.6.1
+gradio==4.37.2
+gradio_client==1.0.2
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.23.4
+idna==3.7
+importlib_resources==6.4.0
+intel-openmp==2021.4.0
+Jinja2==3.1.4
+joblib==1.4.2
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.1
+mdurl==0.1.2
+minijinja==2.0.1
+mkl==2021.4.0
+mpmath==1.3.0
+networkx==3.3
+numpy==1.26.4
+orjson==3.10.6
+packaging==24.1
+pandas==2.2.2
+pillow==10.4.0
+pydantic==2.8.2
+pydantic_core==2.20.1
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.1
+regex==2024.5.15
+requests==2.32.3
+rich==13.7.1
+rpds-py==0.19.0
+ruff==0.5.1
+safetensors==0.4.3
+scikit-learn==1.5.1
+scipy==1.14.0
+semantic-version==2.10.0
+sentence-transformers==3.0.1
+setuptools==69.5.1
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.37.2
+sympy==1.13.0
+tbb==2021.13.0
+threadpoolctl==3.5.0
+tokenizers==0.19.1
+tomlkit==0.12.0
+toolz==0.12.1
+torch==2.3.1
+tqdm==4.66.4
+transformers==4.42.3
+typer==0.12.3
+typing_extensions==4.12.2
+tzdata==2024.1
+ujson==5.10.0
+urllib3==2.2.2
+uvicorn==0.30.1
+watchfiles==0.22.0
+websockets==11.0.3
+wheel==0.43.0