First commit

README.md

@@ -1,6 +1,6 @@
 ---
-title: Aec Tools
-emoji: 🌍
+title: AEC AI Tools - Semantic Search
+emoji: 🏢 
 colorFrom: pink
 colorTo: gray
 sdk: gradio

aecaihub.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b57907b71b89280b8358581f5a8c27c2ed7d99278b7cfde88dfeeed5ca442e1b
+size 2139416

app.py

@@ -0,0 +1,92 @@
+import gradio as gr
+import pandas as pd
+from langchain_community.vectorstores import SKLearnVectorStore
+from langchain_community.embeddings import HuggingFaceBgeEmbeddings
+
+cols = [
+    "Name",
+    "Description",
+    "Category",
+    "AI-Driven",
+    "Champion",
+    "Match score",
+]
+
+persist_path = "aecaihub.parquet"
+
+model_name = "BAAI/bge-small-en-v1.5"
+encode_kwargs = {'normalize_embeddings': True,"show_progress_bar":False,"batch_size":1} # set True to compute cosine similarity
+embeddings_function = HuggingFaceBgeEmbeddings(
+    model_name=model_name,
+    encode_kwargs=encode_kwargs,
+    query_instruction="Represent this sentence for searching relevant passages: "
+)
+
+
+vector_store = SKLearnVectorStore(
+    embedding=embeddings_function, persist_path=persist_path, serializer="parquet"
+)
+
+def predict(query,k):
+
+    docs = vector_store.similarity_search_with_score(query,k = k)
+
+    df_results = []
+    for doc,score in docs:
+        m = doc.metadata
+        result_doc = {
+            "Name":f"**[{m['name']}]({m['url']})**",
+            "Description":doc.page_content,
+            "Category":m["category"],
+            "AI-Driven":m["ai_driven"],
+            "Champion":m["champion"],
+            "Match score":round(1-score,3),
+        }
+        
+        df_results.append(result_doc)
+    df_results = pd.DataFrame(df_results)
+    return df_results
+
+
+examples = [
+    "Tool to generate floor plans"
+    "AI tool for comparing building materials and sustainability",
+    "3D model library with image search function",
+    "AI-powered 3D design tool for architects and interior designers",
+    "Software for extracting 3D models from videos",
+    "AI tool for comprehensive utility data in infrastructure projects",
+    "AI for generating creative content in design projects",
+    "AI tool to convert text into architectural videos",
+    "AI solutions for low carbon design and data mining in architecture",
+    "Software for construction quantity estimation and progress tracking",
+    "AI interior design tool for automatic room designs"
+]
+
+# Create the Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("""
+        # 🏢 AEC AI Hub - Semantic Search Engine
+        This tool uses semantic search to find AI tools for Architecture Engineering and Construction (AEC) based on your question.
+        The database is drawn from the [great work](https://stjepanmikulic.notion.site/AEC-AI-Hub-b6e6eebe88094e0e9b4995da38e96768) of [Stjepan Mikulic](https://www.linkedin.com/in/stjepanmikulic/)
+    """)
+
+    with gr.Row():
+        search_bar = gr.Textbox(label="Ask you question here",scale = 2)
+        k = gr.Slider(minimum=1, maximum=20, value=5, label="Number of results", step=1,interactive=True)
+    examples = gr.Examples(
+            examples,search_bar, label="Examples",
+    )
+    button = gr.Button("🔍 Search")
+    gr.Markdown("## AI Tools")
+    result_df = gr.Dataframe(
+        headers=cols,
+        wrap=True,
+        datatype=["markdown","str","str","str","str","str"],
+        column_widths = ["10%","50%","10%","10%","10%","10%"],
+    )
+
+    (button
+        .click(predict, inputs = [search_bar,k], outputs=[result_df])
+    )
+
+demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+langchain==0.1.0
+sentence-transformers
+huggingface-hub
+gradio
+pandas