more text

app.py

@@ -108,10 +108,11 @@ def write_outreach_links():
     nomic_map_name = "us-congressional-legislation-s1024o256nomic"
     nomic_url = f"{nomic_base_url}/{nomic_map_name}/map"
     hf_url = "https://huggingface.co/hyperdemocracy"
-    st.subheader(":brain: Learn about [hyperdemocracy](https://hyperdemocracy.us)")
-    st.subheader(f":world_map: Visualize with [nomic atlas]({nomic_url})")
-    st.subheader(f":hugging_face: Explore the [huggingface datasets](hf_url)")
-
+    pc_url = "https://www.pinecone.io/blog/serverless"
+    st.subheader(":brain: About [hyperdemocracy](https://hyperdemocracy.us)")
+    st.subheader(f":world_map: Visualize [nomic atlas]({nomic_url})")
+    st.subheader(f":hugging_face: Raw [huggingface datasets](hf_url)")
+    st.subheader(f":evergreen_tree: Index [pinecone serverless](pc_url)")
 
 def group_docs(docs) -> list[tuple[str, list[Document]]]:
     doc_grps = defaultdict(list)
@@ -217,6 +218,30 @@ def escape_markdown(text):
     return text
 
 
+st.title(":classical_building: LegisQA :classical_building:")
+st.header("Explore Congressional Legislation")
+st.write(
+    """When you send a query to LegisQA, it will attempt to retrieve relevant content from the past six congresses ([113th-118th](https://en.wikipedia.org/wiki/List_of_United_States_Congresses)) covering 2013 to the present, pass it to a [large language model (LLM)](https://en.wikipedia.org/wiki/Large_language_model), and generate a response. This technique is known as Retrieval Augmented Generation (RAG). You can read [an academic paper](https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html) or [a high level summary](https://research.ibm.com/blog/retrieval-augmented-generation-RAG) to get more details. Once the response is generated, the retrieved content will be available for inspection with links to the bills and sponsors.
+This technique helps to ground the LLM response by providing context from a trusted source, but it does not guarantee a high quality response. We encourage you to play around. Try different models. Find questions that work and find questions that fail.""")
+
+st.header("Example Queries")
+
+st.write("""
+```
+What are the themes around artificial intelligence?
+```
+
+```
+Write a well cited 3 paragraph essay on food insecurity.
+```
+
+```
+Create a table summarizing the major climate change ideas with columns legis_id, title, idea.
+```
+"""
+)
+
+
 with st.sidebar:
 
     with st.container(border=True):
@@ -269,7 +294,7 @@ vectorstore = load_pinecone_vectorstore()
 format_docs = DOC_FORMATTERS[SS["prompt_version"]]
 
 with st.form("my_form"):
-    st.text_area("Enter question:", key="query")
+    st.text_area("Enter query:", key="query")
     query_submitted = st.form_submit_button("Submit")