Simplify RAG prompt, add common name display, add example runner

- Fix dotenv loading with override=True in app.py and app_database_prep.py
- Simplify the LLM prompt to reduce hallucination (remove complex conditionals and hardcoded references)
- Add explicit region descriptions in prompt (Midwest USA, USA, Africa, India)
- Display common name in species availability info
- Add --examples flag to app.py for running predefined queries programmatically
- Add generate_latex.py for converting example results to LaTeX
- Rebuild vector database with all 4 regions (859 documents)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

app.py

@@ -20,6 +20,7 @@ from anyio.from_thread import start_blocking_portal #For model callback streamin
 from langchain.prompts import SystemMessagePromptTemplate, HumanMessagePromptTemplate, ChatPromptTemplate
 import os
 from dotenv import load_dotenv
+load_dotenv(override=True)
 
 import streamlit as st
 import json
@@ -63,25 +64,27 @@ print("Started")
 
 def get_species_list_from_db(db_name):
     embedding = OpenAIEmbeddings()
-    vectordb_temp = Chroma(persist_directory=db_name, 
+    vectordb_temp = Chroma(persist_directory=db_name,
                   embedding_function=embedding)
     species_list=[]
+    species_to_common_name={}
     for meta in vectordb_temp.get()["metadatas"] :
         try:
             matched_first_species = meta['matched_specie_0']
         except KeyError:
             continue
-        # Since each document is considered as a single chunk, the chunk_index is 0 for all
         species_list.append( matched_first_species)
+        if matched_first_species not in species_to_common_name and 'common_name' in meta:
+            species_to_common_name[matched_first_species] = meta['common_name']
 
-    return species_list
+    return species_list, species_to_common_name
 
 
 
 # default_persist_directory = './db5' # For deployement
 default_persist_directory='./vector-databases-deployed/db5-agllm-data-isu-field-insects-all-species'
 
-species_list=get_species_list_from_db(default_persist_directory)
+species_list, species_to_common_name = get_species_list_from_db(default_persist_directory)
 # default_persist_directory = 'vector-databases/db5-pre-completion' # For Development
 csv_filepath1 = "./agllm-data/corrected/Corrected_supplemented-insect_data-2500-sorted.xlsx"
 csv_filepath2 = "./agllm-data/corrected/Corrected_supplemented-insect_data-remaining.xlsx"
@@ -321,10 +324,12 @@ def initialize_qa_chain(specie_selector, application_mode, model_name, region, d
         
         if available_regions:
             available_regions_list = sorted(list(available_regions))
-            availability_message = f"Information for **{specie_selector}** is available in region(s): **{', '.join(available_regions_list)}**."
+            common_name = species_to_common_name.get(specie_selector, "Unknown")
+            availability_message = f"**Common Name:** {common_name}\n\nInformation for **{specie_selector}** is available in region(s): **{', '.join(available_regions_list)}**."
         else:
             available_regions_list = []
-            availability_message = f"No regional information found for **{specie_selector}** in the database."
+            common_name = species_to_common_name.get(specie_selector, "Unknown")
+            availability_message = f"**Common Name:** {common_name}\n\nNo regional information found for **{specie_selector}** in the database."
     except Exception as e:
         print(f"Error checking region availability: {e}")
         available_regions_list = []
@@ -398,69 +403,28 @@ def initialize_qa_chain(specie_selector, application_mode, model_name, region, d
     # from langchain.chains.combine_documents import create_stuff_documents_chain
     # from langchain.chains import create_retrieval_chain
     
-    # Updated prompt template for multi-part response with region-specific contexts (biosecurity focus)
-    # Determine if this is a Midwest-focused query
-    is_midwest_selected = (region == "Midwest USA")
+    general_system_template = f"""You are an agricultural pest management assistant answering questions about {specie_selector}.
 
-    general_system_template = f"""
-You are an AI assistant specialized in agricultural biosecurity and pest management for {specie_selector}. The user is primarily interested in the '{region}' region.
+The user's selected region is '{region}'. Prioritize information from this region.
 
-The following context has been retrieved from a database organized by region:
+The four regions in the database are:
+- **Midwest USA**: Expert-curated IPM data from the ISU Field Guide, specific to the U.S. Midwest.
+- **USA**: General IPM and management information applicable across the United States.
+- **Africa**: IPM practices relevant to African agricultural systems.
+- **India**: IPM practices relevant to Indian agricultural systems.
+
+Context retrieved from the database (organized by region):
 
 {{context}}
 
 Instructions:
-1. Analyze the user's question in relation to {specie_selector}.
-2. Structure your answer in the following multi-part format:
-
-   **Part 1: Selected Region Information ({region})**
-   {"If you are providing Midwest USA information, note this is expert-curated data from the ISU Field Guide, which is the primary authoritative source for this region." if is_midwest_selected else ""}
-
-   If relevant information exists in the context for the selected region that answers the user's query:
-   Based on your selected region ({region}), for {specie_selector}, [summary of information for selected region] [1].
-
-   If no relevant information exists for the selected region:
-   "Based on the provided documents, there is no specific information for {specie_selector} in your selected region ({region}) regarding your question."
-
-   **Part 2: Other Regions Information** (Only include if information from other regions is available AND relevant to the query)
-   {"Since you selected Midwest USA, note that broader USA-wide management information may also be available. This can provide additional context on how this species is managed across the United States." if is_midwest_selected else ""}
-
-   If you found relevant information from other regions that answers the user's query, include:
-
-   Additionally, information was found for other regions:
-   - In [Other Region Name]: [summary of information that directly answers the user's query] [next reference number].
-   - In [Another Region Name]: [summary of information that directly answers the user's query] [next reference number].
-
-   Only include regions where the information directly addresses the user's question.
-   Use consecutive reference numbers starting from where Part 1 left off.
-   If no other regions have relevant information, omit this part entirely.
-
-   **Part 3: General Knowledge** (Only include if context information is insufficient or incomplete)
-   If the available context does not fully address the query, add:
-
-   Based on my general knowledge as {model_name}: [Your general knowledge insights that directly address the query] [next reference number].
-
-   If the context information is sufficient, omit this part entirely.
-
-3. After providing all parts of your answer, include a References section ONLY for information you actually used:
+- Answer based ONLY on the provided context. If no context exists for a region, do not invent information for it.
+- Start with information from the selected region ('{region}') if available. If not available, clearly state that.
+- Then include relevant information from other regions, clearly labeling which region each piece of information comes from.
+- If the context is insufficient to fully answer the question, you may add brief general knowledge, clearly marked as such.
+- {language_constraint}
 
-References:
-[1] Based on {"ISU Field Guide (Midwest USA)" if is_midwest_selected else f"Expert Curated information about {specie_selector} in {region}"}
-[2] Based on Expert Curated information about {specie_selector} in [Other Region Name]
-[3] Based on Expert Curated information about {specie_selector} in [Another Region Name]
-[x] {model_name}'s inherent knowledge
-
-IMPORTANT:
-- Only include reference numbers that correspond to information you actually used in your answer.
-- Reference numbers should be sequential (1, 2, 3...) based on the order they appear in your answer.
-- If you don't use information from a particular region, don't include a reference for it.
-- If you don't use general knowledge, don't include a reference for it.
-- Every claim with a reference marker [x] must have a corresponding entry in the References section.
-
-4. Apply this language constraint: {language_constraint}
-5. Keep your summaries concise and directly related to the user's question.
-
-User Question about {specie_selector}: {{question}}
+Question: {{question}}
 """
 
     class RegionFormattingLLMChain:
@@ -700,6 +664,55 @@ with gr.Blocks(theme=gr.themes.Soft())  as demo:
 
     # When the user clicks the clear button
     # clear.click(lambda: None, None, chatbot, queue=False).success(init_history, [state], [state])
-    if __name__ == "__main__":
-    # demo.launch()
+
+
+def run_examples():
+    """Run predefined examples and save results for paper."""
+    import json
+    from datetime import datetime
+
+    examples = [
+        {"species": "Striga asiatica", "region": "USA",         "model": "Llama-3 70B", "mode": "Researcher", "question": "What is the most effective way to manage Striga in my maize field?"},
+        {"species": "Striga asiatica", "region": "Africa",      "model": "Llama-3 70B", "mode": "Researcher", "question": "What is the most effective way to manage Striga in my maize field?"},
+        {"species": "Striga asiatica", "region": "Midwest USA", "model": "Llama-3 70B", "mode": "Researcher", "question": "What is the most effective way to manage Striga in my maize field?"},
+    ]
+
+    results = []
+    for i, ex in enumerate(examples, 1):
+        print(f"\n{'='*60}")
+        print(f"Example {i}: {ex['species']} | Region: {ex['region']} | Model: {ex['model']}")
+        print(f"Question: {ex['question']}")
+        print(f"{'='*60}")
+
+        qa_chain, availability_msg = initialize_qa_chain(
+            ex["species"], ex["mode"], ex["model"], ex["region"]
+        )
+        print(availability_msg)
+
+        result = qa_chain({"question": ex["question"], "chat_history": []})
+        answer = result["answer"]
+        print(f"\n--- Answer ---\n{answer}")
+
+        results.append({
+            "species": ex["species"],
+            "region": ex["region"],
+            "model": ex["model"],
+            "mode": ex["mode"],
+            "question": ex["question"],
+            "availability": availability_msg,
+            "answer": answer,
+        })
+
+    output_file = f"examples-work-out/example_results_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json"
+    os.makedirs("examples-work-out", exist_ok=True)
+    with open(output_file, 'w') as f:
+        json.dump(results, f, indent=2)
+    print(f"\n\nResults saved to {output_file}")
+
+
+if __name__ == "__main__":
+    import sys
+    if "--examples" in sys.argv:
+        run_examples()
+    else:
         demo.queue().launch(allowed_paths=["/"], share=False, show_error=True)

app_database_prep.py

@@ -19,6 +19,7 @@ langchain.debug=True # TODO: DOUBLE CHECK
 system_message = {"role": "system", "content": "You are a helpful assistant."} # TODO: double check how this plays out later. 
 import os
 from dotenv import load_dotenv
+load_dotenv(override=True)
 
 import streamlit as st
 

examples-work-out/example_results_20260212_105524.json

@@ -0,0 +1,29 @@
+[
+  {
+    "species": "Striga asiatica",
+    "region": "USA",
+    "model": "Llama-3 70B",
+    "mode": "Researcher",
+    "question": "What is the most effective way to manage Striga in my maize field?",
+    "availability": "**Common Name:** Witch weed\n\nInformation for **Striga asiatica** is available in region(s): **Africa, USA**.",
+    "answer": "Based on the provided context from the USA region, the most effective way to manage Striga in your maize field is through an integrated management strategy that combines cultural, chemical, and biological controls.\n\nCultural control practices that can be employed include crop rotation with non-host crops to reduce Striga seed banks in the soil, deep plowing to bury Striga seeds to depths where they cannot germinate, and using resistant crop varieties to limit the impact of Striga infestations. Maintaining high soil fertility can also help crops outgrow the parasitic effects of Striga.\n\nChemical control options include the use of pre-emergent and post-emergent herbicides, such as imazapyr and glyphosate, which have been effective when used appropriately.\n\nBiological control options, although still in the experimental stage, involve the use of certain fungi and bacteria that can attack Striga seeds or seedlings.\n\nIt is essential to monitor and detect Striga infestations early, as this is crucial for effective management. Regular field inspections can help identify early signs of infestation.\n\nNo specific information is available from the Midwest USA region, Africa, or India that provides more specific guidance for maize fields. However, it is generally known that Striga management requires a long-term, multi-faceted approach that takes into account the specific conditions of the field and the crop being grown.\n\nIn summary, a combination of cultural, chemical, and biological controls, along with early detection and monitoring, is the most effective way to manage Striga in your maize field."
+  },
+  {
+    "species": "Striga asiatica",
+    "region": "Africa",
+    "model": "Llama-3 70B",
+    "mode": "Researcher",
+    "question": "What is the most effective way to manage Striga in my maize field?",
+    "availability": "**Common Name:** Witch weed\n\nInformation for **Striga asiatica** is available in region(s): **Africa, USA**.",
+    "answer": "Based on the provided context, here's a comprehensive answer to your question:\n\n**From Africa:**\nUnfortunately, there is no specific information on managing Striga in maize fields in the African context. The provided documents from Africa primarily focus on the description of Striga asiatica, its morphology, and growth habits.\n\n**From USA:**\nHowever, we can draw insights from the USA context, which provides more information on management strategies. An integrated approach combining cultural, chemical, and biological controls is recommended for effective long-term management of Striga asiatica (Document 1 from USA). \n\n**Cultural Control/Management Practices:**\nCrop rotation with non-host crops can help reduce Striga seed banks in the soil (Document 3 from USA). Deep plowing can bury Striga seeds to depths where they cannot germinate. Using resistant crop varieties can limit the impact of Striga infestations. Maintaining high soil fertility can help crops outgrow the parasitic effects of Striga (Document 3 from USA).\n\n**Chemical Control Options:**\nPre-emergent and post-emergent herbicides can be used to control Striga infestations. Herbicides such as imazapyr and glyphosate have been effective when used appropriately (Document 2 from USA).\n\n**Biological Control Options:**\nThere are ongoing studies into the use of certain fungi and bacteria that can attack Striga seeds or seedlings, though these are not widely implemented yet (Document 2 from USA).\n\n**General Knowledge:**\nIt is essential to monitor your maize field regularly to detect Striga infestations early, as this can help prevent the spread of the parasite and reduce the impact on your crop.\n\nIn summary, while there is no specific information on managing Striga in maize fields in the African context, an integrated approach combining cultural, chemical, and biological controls, as suggested in the USA context, can be a effective way to manage Striga in your maize field. Regular monitoring, crop rotation"
+  },
+  {
+    "species": "Striga asiatica",
+    "region": "Midwest USA",
+    "model": "Llama-3 70B",
+    "mode": "Researcher",
+    "question": "What is the most effective way to manage Striga in my maize field?",
+    "availability": "**Common Name:** Witch weed\n\nInformation for **Striga asiatica** is available in region(s): **Africa, USA**.",
+    "answer": "Based on the provided context, I'll provide an answer tailored to the Midwest USA region.\n\n**Midwest USA:** Unfortunately, there is no specific information available in the provided context for the Midwest USA region that directly addresses the most effective way to manage Striga in a maize field.\n\n**USA:** However, we can draw from general IPM and management information applicable across the United States. According to Document 1 from USA, integrated management strategies combining cultural, chemical, and biological controls are recommended for effective long-term management of Striga asiatica. This suggests that a multi-faceted approach may be the most effective way to manage Striga in a maize field.\n\n**Cultural Control/Management Practices (USA):** Document 3 from USA provides some cultural control and management practices that can be employed to manage Striga infestations. These include:\n\n* Crop rotation with non-host crops to reduce Striga seed banks in the soil\n* Deep plowing to bury Striga seeds to depths where they cannot germinate\n* Use of resistant crop varieties to limit the impact of Striga infestations\n* Maintaining high soil fertility to help crops outgrow the parasitic effects of Striga\n\n**Chemical Control Options (USA):** Document 2 from USA mentions that pre-emergent and post-emergent herbicides can be used to control Striga infestations. Herbicides such as imazapyr and glyphosate have been effective when used appropriately.\n\n**Biological Control Options (USA):** While not widely implemented, there are ongoing studies into the use of certain fungi and bacteria that can attack Striga seeds or seedlings (Document 2 from USA).\n\n**General Knowledge:** It is essential to note that Striga management requires a long-term strategy, as the seeds can remain viable in the soil for many years. A combination of these methods, tailored to the specific field conditions and maize variety, may be the most effective way to manage Striga in a maize"
+  }
+]

examples-work-out/example_results_20260212_105524.tex

@@ -0,0 +1,156 @@
+\documentclass[11pt]{article}
+\usepackage[margin=1in]{geometry}
+\usepackage{tcolorbox}
+\usepackage{booktabs}
+\usepackage{hyperref}
+
+\title{AgLLM -- Example Queries and Responses}
+\author{}
+\date{}
+
+\begin{document}
+\maketitle
+
+The following examples demonstrate AgLLM responses for the species \textit{Striga asiatica} (Witch weed) across different regional configurations. Each example shows the user query and the system's response, which retrieves region-specific information from the vector database and generates an answer using the selected LLM.
+
+
+\subsection*{Example 1}
+
+\begin{tcolorbox}[colback=gray!5, colframe=gray!60, title=Configuration]
+\begin{tabular}{@{}ll@{}}
+\textbf{Species:}           & Striga asiatica \\
+\textbf{Common Name:}       & N/A \\
+\textbf{Selected Region:}   & USA \\
+\textbf{Available Regions:}  & Africa, USA \\
+\textbf{Model:}             & Llama-3 70B \\
+\textbf{Mode:}              & Researcher \\
+\end{tabular}
+\end{tcolorbox}
+
+\begin{tcolorbox}[colback=blue!3, colframe=blue!40, title=User Query]
+What is the most effective way to manage Striga in my maize field?
+\end{tcolorbox}
+
+\begin{tcolorbox}[colback=green!3, colframe=green!40, title=AgLLM Response]
+Based on the provided context from the USA region, the most effective way to manage Striga in your maize field is through an integrated management strategy that combines cultural, chemical, and biological controls.
+
+\medskip
+Cultural control practices that can be employed include crop rotation with non-host crops to reduce Striga seed banks in the soil, deep plowing to bury Striga seeds to depths where they cannot germinate, and using resistant crop varieties to limit the impact of Striga infestations. Maintaining high soil fertility can also help crops outgrow the parasitic effects of Striga.
+
+\medskip
+Chemical control options include the use of pre-emergent and post-emergent herbicides, such as imazapyr and glyphosate, which have been effective when used appropriately.
+
+\medskip
+Biological control options, although still in the experimental stage, involve the use of certain fungi and bacteria that can attack Striga seeds or seedlings.
+
+\medskip
+It is essential to monitor and detect Striga infestations early, as this is crucial for effective management. Regular field inspections can help identify early signs of infestation.
+
+\medskip
+No specific information is available from the Midwest USA region, Africa, or India that provides more specific guidance for maize fields. However, it is generally known that Striga management requires a long-term, multi-faceted approach that takes into account the specific conditions of the field and the crop being grown.
+
+\medskip
+In summary, a combination of cultural, chemical, and biological controls, along with early detection and monitoring, is the most effective way to manage Striga in your maize field.
+\end{tcolorbox}
+
+\vspace{1em}
+
+\subsection*{Example 2}
+
+\begin{tcolorbox}[colback=gray!5, colframe=gray!60, title=Configuration]
+\begin{tabular}{@{}ll@{}}
+\textbf{Species:}           & Striga asiatica \\
+\textbf{Common Name:}       & N/A \\
+\textbf{Selected Region:}   & Africa \\
+\textbf{Available Regions:}  & Africa, USA \\
+\textbf{Model:}             & Llama-3 70B \\
+\textbf{Mode:}              & Researcher \\
+\end{tabular}
+\end{tcolorbox}
+
+\begin{tcolorbox}[colback=blue!3, colframe=blue!40, title=User Query]
+What is the most effective way to manage Striga in my maize field?
+\end{tcolorbox}
+
+\begin{tcolorbox}[colback=green!3, colframe=green!40, title=AgLLM Response]
+Based on the provided context, here's a comprehensive answer to your question:
+
+\medskip
+\textbf{From Africa:}
+Unfortunately, there is no specific information on managing Striga in maize fields in the African context. The provided documents from Africa primarily focus on the description of Striga asiatica, its morphology, and growth habits.
+
+\medskip
+\textbf{From USA:}
+However, we can draw insights from the USA context, which provides more information on management strategies. An integrated approach combining cultural, chemical, and biological controls is recommended for effective long-term management of Striga asiatica (Document 1 from USA). 
+
+\medskip
+\textbf{Cultural Control/Management Practices:}
+Crop rotation with non-host crops can help reduce Striga seed banks in the soil (Document 3 from USA). Deep plowing can bury Striga seeds to depths where they cannot germinate. Using resistant crop varieties can limit the impact of Striga infestations. Maintaining high soil fertility can help crops outgrow the parasitic effects of Striga (Document 3 from USA).
+
+\medskip
+\textbf{Chemical Control Options:}
+Pre-emergent and post-emergent herbicides can be used to control Striga infestations. Herbicides such as imazapyr and glyphosate have been effective when used appropriately (Document 2 from USA).
+
+\medskip
+\textbf{Biological Control Options:}
+There are ongoing studies into the use of certain fungi and bacteria that can attack Striga seeds or seedlings, though these are not widely implemented yet (Document 2 from USA).
+
+\medskip
+\textbf{General Knowledge:}
+It is essential to monitor your maize field regularly to detect Striga infestations early, as this can help prevent the spread of the parasite and reduce the impact on your crop.
+
+\medskip
+In summary, while there is no specific information on managing Striga in maize fields in the African context, an integrated approach combining cultural, chemical, and biological controls, as suggested in the USA context, can be a effective way to manage Striga in your maize field. Regular monitoring, crop rotation
+\end{tcolorbox}
+
+\vspace{1em}
+
+\subsection*{Example 3}
+
+\begin{tcolorbox}[colback=gray!5, colframe=gray!60, title=Configuration]
+\begin{tabular}{@{}ll@{}}
+\textbf{Species:}           & Striga asiatica \\
+\textbf{Common Name:}       & N/A \\
+\textbf{Selected Region:}   & Midwest USA \\
+\textbf{Available Regions:}  & Africa, USA \\
+\textbf{Model:}             & Llama-3 70B \\
+\textbf{Mode:}              & Researcher \\
+\end{tabular}
+\end{tcolorbox}
+
+\begin{tcolorbox}[colback=blue!3, colframe=blue!40, title=User Query]
+What is the most effective way to manage Striga in my maize field?
+\end{tcolorbox}
+
+\begin{tcolorbox}[colback=green!3, colframe=green!40, title=AgLLM Response]
+Based on the provided context, I'll provide an answer tailored to the Midwest USA region.
+
+\medskip
+\textbf{Midwest USA:} Unfortunately, there is no specific information available in the provided context for the Midwest USA region that directly addresses the most effective way to manage Striga in a maize field.
+
+\medskip
+\textbf{USA:} However, we can draw from general IPM and management information applicable across the United States. According to Document 1 from USA, integrated management strategies combining cultural, chemical, and biological controls are recommended for effective long-term management of Striga asiatica. This suggests that a multi-faceted approach may be the most effective way to manage Striga in a maize field.
+
+\medskip
+\textbf{Cultural Control/Management Practices (USA):} Document 3 from USA provides some cultural control and management practices that can be employed to manage Striga infestations. These include:
+
+\medskip
+\textbullet\ Crop rotation with non-host crops to reduce Striga seed banks in the soil
+\textbullet\ Deep plowing to bury Striga seeds to depths where they cannot germinate
+\textbullet\ Use of resistant crop varieties to limit the impact of Striga infestations
+\textbullet\ Maintaining high soil fertility to help crops outgrow the parasitic effects of Striga
+
+\medskip
+\textbf{Chemical Control Options (USA):} Document 2 from USA mentions that pre-emergent and post-emergent herbicides can be used to control Striga infestations. Herbicides such as imazapyr and glyphosate have been effective when used appropriately.
+
+\medskip
+\textbf{Biological Control Options (USA):} While not widely implemented, there are ongoing studies into the use of certain fungi and bacteria that can attack Striga seeds or seedlings (Document 2 from USA).
+
+\medskip
+\textbf{General Knowledge:} It is essential to note that Striga management requires a long-term strategy, as the seeds can remain viable in the soil for many years. A combination of these methods, tailored to the specific field conditions and maize variety, may be the most effective way to manage Striga in a maize
+\end{tcolorbox}
+
+\vspace{1em}
+
+
+\end{document}

examples-work-out/generate_latex.py

@@ -0,0 +1,130 @@
+"""
+Generate a LaTeX file from example results JSON.
+Usage: python generate_latex.py example_results_20260212_105524.json
+"""
+import json
+import sys
+import os
+import re
+
+
+def escape_latex(text):
+    """Escape special LaTeX characters."""
+    replacements = [
+        ('\\', r'\textbackslash{}'),
+        ('&', r'\&'),
+        ('%', r'\%'),
+        ('$', r'\$'),
+        ('#', r'\#'),
+        ('_', r'\_'),
+        ('{', r'\{'),
+        ('}', r'\}'),
+        ('~', r'\textasciitilde{}'),
+        ('^', r'\textasciicircum{}'),
+    ]
+    for old, new in replacements:
+        text = text.replace(old, new)
+    return text
+
+
+def md_bold_to_latex(text):
+    """Convert **bold** markdown to LaTeX \\textbf{}."""
+    return re.sub(r'\*\*(.+?)\*\*', r'\\textbf{\1}', text)
+
+
+def format_answer(text):
+    """Convert answer text to LaTeX, handling markdown-style formatting."""
+    text = escape_latex(text)
+    text = md_bold_to_latex(text)
+    # Convert bullet points
+    text = re.sub(r'^\* ', r'\\textbullet\\ ', text, flags=re.MULTILINE)
+    # Paragraph breaks
+    text = text.replace('\n\n', '\n\n\\medskip\n')
+    return text
+
+
+def generate_latex(results, output_path):
+    examples_tex = ""
+
+    for i, ex in enumerate(results, 1):
+        # Extract common name from availability markdown
+        common_name_match = re.search(r'\*\*Common Name:\*\* (.+?)\\n', ex.get('availability', ''))
+        common_name = common_name_match.group(1) if common_name_match else 'N/A'
+
+        # Extract available regions
+        regions_match = re.search(r'available in region\(s\): \*\*(.+?)\*\*', ex.get('availability', ''))
+        available_regions = regions_match.group(1) if regions_match else 'N/A'
+
+        question = escape_latex(ex['question'])
+        answer = format_answer(ex['answer'])
+        species = escape_latex(ex['species'])
+        region = escape_latex(ex['region'])
+        model = escape_latex(ex['model'])
+        mode = escape_latex(ex['mode'])
+        common_name = escape_latex(common_name)
+        available_regions = escape_latex(available_regions)
+
+        examples_tex += rf"""
+\subsection*{{Example {i}}}
+
+\begin{{tcolorbox}}[colback=gray!5, colframe=gray!60, title=Configuration]
+\begin{{tabular}}{{@{{}}ll@{{}}}}
+\textbf{{Species:}}           & {species} \\
+\textbf{{Common Name:}}       & {common_name} \\
+\textbf{{Selected Region:}}   & {region} \\
+\textbf{{Available Regions:}}  & {available_regions} \\
+\textbf{{Model:}}             & {model} \\
+\textbf{{Mode:}}              & {mode} \\
+\end{{tabular}}
+\end{{tcolorbox}}
+
+\begin{{tcolorbox}}[colback=blue!3, colframe=blue!40, title=User Query]
+{question}
+\end{{tcolorbox}}
+
+\begin{{tcolorbox}}[colback=green!3, colframe=green!40, title=AgLLM Response]
+{answer}
+\end{{tcolorbox}}
+
+\vspace{{1em}}
+"""
+
+    latex = rf"""\documentclass[11pt]{{article}}
+\usepackage[margin=1in]{{geometry}}
+\usepackage{{tcolorbox}}
+\usepackage{{booktabs}}
+\usepackage{{hyperref}}
+
+\title{{AgLLM -- Example Queries and Responses}}
+\author{{}}
+\date{{}}
+
+\begin{{document}}
+\maketitle
+
+The following examples demonstrate AgLLM responses for the species \textit{{Striga asiatica}} (Witch weed) across different regional configurations. Each example shows the user query and the system's response, which retrieves region-specific information from the vector database and generates an answer using the selected LLM.
+
+{examples_tex}
+
+\end{{document}}
+"""
+
+    with open(output_path, 'w') as f:
+        f.write(latex)
+    print(f"LaTeX file generated: {output_path}")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: python generate_latex.py <results.json>")
+        sys.exit(1)
+
+    input_file = sys.argv[1]
+    if not os.path.isabs(input_file):
+        input_file = os.path.join(os.path.dirname(__file__), input_file)
+
+    with open(input_file) as f:
+        results = json.load(f)
+
+    output_path = input_file.replace('.json', '.tex')
+    generate_latex(results, output_path)

species-organized/PestID Species - Organized.xlsx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ea15614f571729ba9f24512ac8498576c2b0ebbade382797bf275e159a4dd2
-size 74872
+oid sha256:d9b0e9af388f34b0452a7df83a969df19da056c5e6ff6f03eef2ef8fe6556607
+size 75571

species-organized/~$PestID Species - Organized.xlsx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a56509277035f865d54f697560634f21da3e36da0c983cc6f72ebb79ec3b73eb
-size 165

vector-databases-deployed/db5-agllm-data-isu-field-insects-all-species/{ccf8b07b-b9f2-468a-812a-2d7f01ec2bb8 → 6934d416-b9d8-4bd9-b666-9621dc3ed67f}/length.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e2dcff542de95352682dc186432e98f0188084896773f1973276b0577d5305
+oid sha256:9ddf37297936a4b972cfb2c49f1215f38c32ec782e45fbfce6590540e91dbd02
 size 40000

vector-databases-deployed/db5-agllm-data-isu-field-insects-all-species/chroma.sqlite3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eb79a00bf67e95a8a48172339e165eb674224bbba53b02d4b5163a9a315650a
-size 10674176
+oid sha256:0012d7100fc6b0082f7f8744c90432a2b9d55fa9250274c7e57bd3c3160d5ddc
+size 10678272