adding ben hogan

.gitattributes

@@ -36,3 +36,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 resources/design-by-fire.pdf filter=lfs diff=lfs merge=lfs -text
 resources/lets-talk.pdf filter=lfs diff=lfs merge=lfs -text
 resources/progit.pdf filter=lfs diff=lfs merge=lfs -text
+resources filter=lfs diff=lfs merge=lfs -text
+resources/Ben_Hogans_Five_Lessons.pdf filter=lfs diff=lfs merge=lfs -text
+resources/How_To_Win_Friends_And_Influence_People_-_Dale_Carnegie.pdf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
-title: Pyrocene
-emoji: 🌖
+title: Ben  Hogan
+emoji: 🏌🏽
 colorFrom: green
 colorTo: green
 sdk: gradio

resources/Ben_Hogans_Five_Lessons.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7131303648e0817fe35bc9fcacfe333420e8f4f4f6b5e7cf2b0ceb2914c13e9
+size 3247151

src/app.py

@@ -23,8 +23,8 @@ K = 5
 USE_VERBOSE = True
 API_KEY = os.environ["OPENAI_API_KEY"]
 system_template = """
-The context below contains excerpts from 'Design by Fire,' by Emily Elizabeth Schlickman and Brett Milligan. You must only use the information in the context below to formulate your response. If there is not enough information to formulate  a response, you must respond with
-"I'm sorry, but I can't find the answer to your question in, the book Design by Fire."
+The context below contains excerpts from 'Ben Hogan's Five Lessions'. You must only use the information in the context below to formulate your response. If there is not enough information to formulate a response, you must respond with
+"I'm sorry, but I can't find the answer to your question in, Ben Hogan's Five Lessons."
 
 Here is the context:
 {context}
@@ -43,7 +43,7 @@ class AnswerConversationBufferMemory(ConversationBufferMemory):
     return super(AnswerConversationBufferMemory, self).save_context(inputs,{'response': outputs['answer']})
 
 def getretriever():
-  with open("./resources/design-by-fire.pdf", 'rb') as uploaded_file:
+  with open("./resources/Ben_Hogans_Five_Lessons.pdf", 'rb') as uploaded_file:
     try:
       file = read_file(uploaded_file)
     except Exception as e:
@@ -95,26 +95,19 @@ def load_chain(inputs = None):
     combine_docs_chain_kwargs={"prompt": qa_prompt})
   return chain
 
-CSS ="""
-.contain { display: flex; flex-direction: column; }
-.gradio-container { height: 100vh !important; }
-#component-0 { height: 100%; }
-#chatbot { flex-grow: 1; overflow: auto;}
-"""
-
 with gr.Blocks() as block:
   with gr.Row():
     with gr.Column(scale=0.75):
       with gr.Row():
-        gr.Markdown("<h1>Design by Fire</h1>")
+        gr.Markdown("<h1>Ben Hogan's Five Lessons</h1>")
       with gr.Row():
-        gr.Markdown("by Emily Elizabeth Schlickman and Brett Milligan")
+        gr.Markdown("by Ben Hogan")
       chatbot = gr.Chatbot(elem_id="chatbot").style(height=600)
 
       with gr.Row():
           message = gr.Textbox(
               label="",
-              placeholder="Design by Fire",
+              placeholder="Ask Ben...",
               lines=1,
           )
       with gr.Row():
@@ -129,11 +122,11 @@ with gr.Blocks() as block:
     with gr.Column(scale=0.25):
       with gr.Row():
         gr.Markdown("<h1><center>Suggestions</center></h1>")
-      ex1 = gr.Button(value="What are the main factors and trends discussed in the book that contribute to the changing behavior of wildfires?", variant="primary")
+      ex1 = gr.Button(value="What is this book about?", variant="primary")
       ex1.click(getanswer, inputs=[chain_state, ex1, state], outputs=[chatbot, state, message])
-      ex2 = gr.Button(value="How does the book explore the relationship between fire and different landscapes, such as wilderness and urban areas?", variant="primary")
+      ex2 = gr.Button(value="What are the core fundamentals Ben teaches?", variant="primary")
       ex2.click(getanswer, inputs=[chain_state, ex2, state], outputs=[chatbot, state, message])
-      ex3 = gr.Button(value="What are the three approaches to designing with fire that the book presents?", variant="primary")
+      ex3 = gr.Button(value="How did Ben change the way the game is taught?", variant="primary")
       ex3.click(getanswer, inputs=[chain_state, ex3, state], outputs=[chatbot, state, message])
 
 block.launch(debug=True)

src/core/embedding.py

@@ -1,7 +1,7 @@
 from typing import List, Type
 
 from langchain.docstore.document import Document
-from langchain.embeddings import OpenAIEmbeddings
+from langchain.embeddings import HuggingFaceBgeEmbeddings
 from langchain.embeddings.base import Embeddings
 from langchain.vectorstores import VectorStore
 from langchain.vectorstores.faiss import FAISS
@@ -50,27 +50,16 @@ class FolderIndex:
 def embed_files(
     files: List[File], embedding: str, vector_store: str, **kwargs
 ) -> FolderIndex:
-    """Embeds a collection of files and stores them in a FolderIndex."""
-
-    supported_embeddings: dict[str, Type[Embeddings]] = {
-        "openai": OpenAIEmbeddings,
-        "debug": FakeEmbeddings,
-    }
-    supported_vector_stores: dict[str, Type[VectorStore]] = {
-        "faiss": FAISS,
-        "debug": FakeVectorStore,
-    }
-
-    if embedding in supported_embeddings:
-        _embeddings = supported_embeddings[embedding](**kwargs)
-    else:
-        raise NotImplementedError(f"Embedding {embedding} not supported.")
-
-    if vector_store in supported_vector_stores:
-        _vector_store = supported_vector_stores[vector_store]
-    else:
-        raise NotImplementedError(f"Vector store {vector_store} not supported.")
-
+    model_name = "BAAI/bge-small-en"
+    model_kwargs = {'device': 'cpu'}
+    encode_kwargs = {'normalize_embeddings': True} # set True to compute cosine similarity
+    model_norm = HuggingFaceBgeEmbeddings(
+        model_name=model_name,
+        model_kwargs=model_kwargs,
+        encode_kwargs=encode_kwargs
+    )
+    # embeddings = OpenAIEmbeddings
+    embeddings = model_norm
     return FolderIndex.from_files(
-        files=files, embeddings=_embeddings, vector_store=_vector_store
+        files=files, embeddings=embeddings, vector_store=FAISS
     )