Update app.py

app.py

@@ -35,7 +35,7 @@ TOTAL_SUMMARIZED_WORDS = 0
 
 def generate_graph_snippet(placeholder_text: str, context: str, initial_query: str, crumbs: str) -> str:    
     prompt = f"""
-Generate a full htmal code (including css and javascript) code displaying a simple but effective and elegant graph based on the following requirements:
+Generate a full html code (including css and javascript) code displaying a simple but effective and elegant graph based on the following requirements:
 {placeholder_text}
 
 It will be integrated in a broader report (focus on the graph formatting though) about:
@@ -127,7 +127,7 @@ Keep in mind the:
 {crumbs}
 
 // Requirements
-- use standard mermaid visual rendering (ex: flowchart, sequence, gantt, pie, mindmap, xychart)
+- use standard mermaid visual rendering (ex: flowchart, sequence, gantt, pie, mindmap)
 - no introduction, conclusions or code fences -> Output the result directly
 - create only the content for the mermaid
 - no comments of #color coding and classes inside the mermaid code generated, it's supposed to be only focused on the mermaid code required to render it
@@ -144,7 +144,7 @@ instead, use
 G --> H[Performance Evaluation - 45% Speed Improvement, 35% Risk Profiling, 50% Fraud Detection]
 - Similarly, do not use the symbol | in the mermaid code, it would create an error 
 - Do not use the gantt chart visual placeholder to generate a graph (ex: barchart), Gantt charts should only be used for timelines / project plans
-Note: Visual placeholders are solely supposed to generate diagrams, for graphs, you should use the xychart that are focused on this purpose.
+Note: Visual placeholders are solely supposed to generate diagrams not for graphs.
 - use only this type of quotation marks: ", others would lead to failure to render
 - if you need to render a quotation mark inside the text of the diagram make sure to add escapechar so that mermaid interprets it correctly
 - do not use commas in the content of each object / nodes, they will create rendering issues 
@@ -153,14 +153,6 @@ Note: Visual placeholders are solely supposed to generate diagrams, for graphs,
 // Examples
 Note: Pay attention for each example to what type of parenthesis / bracket is used and respect it scrupulously
 
--- xy chart --
-xychart-beta
-    title "Sales Revenue"
-    x-axis [jan, feb, mar, apr, may, jun, jul, aug, sep, oct, nov, dec]
-    y-axis "Revenue (in $)" 4000 --> 11000
-    bar [5000, 6000, 7500, 8200, 9500, 10500, 11000, 10200, 9200, 8500, 7000, 6000]
-    line [5000, 6000, 7500, 8200, 9500, 10500, 11000, 10200, 9200, 8500, 7000, 6000]
-
 -- flowchart --
 Important:
 - If the flow is "broader" than deep (>3 branches at the same level), choose LR (Left Right)
@@ -708,17 +700,12 @@ def generate_final_report(initial_query: str, context: str, reportstyle: str, le
     word_count = pages * 500
     prompt = (f"""
 // Instructions:
-- We want to incorporate as many relevant numbers, statistics, factual references, quotes from the sources, 
-- Explicit mentions of organizations, tools, projects, or people from the crumb data as possible.
-- In your writing, do the following:
-1. Integrate numbers, quotes, and factual references systematically.
+1. Integrate numbers, quotes, and factual references systematically (We want to incorporate as many relevant numbers, statistics, factual references, quotes from the sources)
 2. Whenever you mention a figure or quote, add an inline reference [x] matching its source from the references.
 3. Specifically name relevant organizations, tools, project names, and people encountered in the crumbs or learnings.
-4. This is for academic purposes, so thorough citations and referencing are essential.
-5. Explicitly use the names (organizations, people, project, application, tools...) mentioned in the sources, we need this for academic correctness
-6. Focus on reputable sources that will not be disputed (social media posts cannot be an opposable sources, but some of them may mention reputable sources)
-
-
+Note: This is for academic purposes, so thorough citations and referencing are essential.
+4. Focus on reputable sources that will not be disputed (social media posts cannot be an opposable sources, but some of them may mention reputable sources)
+5. It must follow this writing style {reportstyle}.
 // Sources
 Use the following learnings and merged reference details from a deep research process on:
 '{initial_query}'
@@ -729,14 +716,14 @@ Produce a comprehensive research report in html format.
 The report should be very detailed and lengthy — approximately the equivalent of {pages} pages (or {word_count} words) when printed.
 
 // Requirements
-- It must include inline citations (e.g., [1], [2], etc.) from real sources in the context
-- It must follow this writing style {reportstyle}.
+- It must include inline citations (e.g., [1], [2], etc.) from real sources provided in the search results below
+- Do not add any inline citations reference in the placeholders descriptions below (visual, graph or focus)
 - Don't make too large blocks, skip lines and add line breaks when changing topic.
-- name projects, products, organisations and people with their titles - make it REAL
 - The report must include at least {round(pages/3,0)} tables from the sources used (add citations if necessary) and use facts and figures extensively to ground the analysis.
 - For the numbering of titles or numbered lists, use numbers (ex: 1.) and sub-units (1.1, 1.2... 1.1.1...,1.1.2...).
+Note: Exclude the use of html numbered lists format, they don't get correctly implemented. Use plain text format for numbering of sections and sub-sections
 - For the reference citations, add systematically the urls from the Learnings (no need to put them in numbered list format since we alredy have the [x] that serves as number list)
-IMPORTANT: Do not make false references / citations. It has to be grounded from the sources from the results of the searches below (no example.com/... type references!)
+- Do not make false references / citations. It has to be grounded from the sources from the results of the searches below (no example.com/... type references!)
 - Put paragraphs, sentences that are part of the same section in a div tag, this will be used for formatting.
 - Text Alignment has to be to the left, including for the titles
 - Add on top of the report the report title (with the <h1> tag) - this is the only part that should be centered (in-line style)
@@ -747,10 +734,13 @@ IMPORTANT: Do not make false references / citations. It has to be grounded from
   <h4> for bulletpoint title (ex: <h4>item to detail:</h4>details ...)
 - Use inline formatting for the tables with homogeneous border and colors
 - Avoid Chinese characters in the output (use the Pinyin version) since they won't display correcly in the pdf (black boxes)
-- Exclude the use of html numbered lists format, they don't get correctly implemented. Use plain text format for numbering of sections and sub-sections
+
+--------------- Placeholders -----------
+In order to enrich the content, within the core sections (between introduction and conclusion), you can inject some placeholders that will be developped later on.
+There are 3 types: visual, graphs, focus - each with their own purpose
 
 // Visual placeholders
-- Since the generation of visuals (excluding tables) like graph or charts cannot be done through text, create special visual placeholders that will be rendered in mermaid afterwards based on your guidance:
+- Since the generation of visuals (excluding tables) cannot be done through text, create special visual placeholders that will be rendered in mermaid afterwards based on your guidance:
 [[Visual Placeholder n:
 - Purpose of this visual is:...
 - Relevant data to generate it:...
@@ -758,37 +748,34 @@ IMPORTANT: Do not make false references / citations. It has to be grounded from
 with n as the reference number
 Important: after [[ put "Visual Placeholder n:" explicitly (with n as the ref number of the focus box created). This will be used in a regex
 
-- the only types of mermaid diagram that can be generated are: flowchart, sequence, gantt, pie, mindmap, xy-chart // Take this into consideration when providing the instructions for the diagram
+- the only types of mermaid diagram that can be generated are: flowchart, sequence, gantt, pie, mindmap (no charts) // Take this into consideration when providing the instructions for the diagram
 - do not make reference in the report to "visual placeholders" just mention visuals.
-- in the placeholder, no need to add the references to the source, but make sure ALL of the data points required has a source from the learning and reference material hereafter 
+- in the placeholder, no need to add the references to the source or its ref number, but make sure ALL of the data points required has a source from the learning and reference material hereafter 
 - these placeholders text should contain:
     o the purpose of the future visual 
     o the relevant data to generate it
-- there should be at least {round(pages/4,0)} of these visuals placeholders within the report
-- 2 visual placeholders cannot be in the same or in 2 consecutive sections
-Note: the placeholders will then be processed separtely by a llm to generate the specific code to display each of them so the instruction need to be clear enough.
+- there should be at least {round(pages/4,0)} of these visuals placeholders within the report (all between introduction and conclusion)
+- 2 visual placeholders cannot be in the same section 
+Note: the placeholders will then be processed separately by a llm to generate the specific code to display each of them so the instruction need to be clear enough.
 
 // Graph placeholders
-- Create special graphe placeholders that will be rendered in d3.js afterwards based on your guidance:
+- Create special graph placeholders that will be rendered in d3.js afterwards based on your guidance:
 [[Graph Placeholder n:
 - Purpose of this graph is:...
 - Relevant data to generate it:...
-- Visual guidance:...
 ]]
 with n as the reference number
 Important: after [[ put "Graph Placeholder n:" explicitly (with n as the ref number of the focus box created). This will be used in a regex
 
-- All types of graphs from d3.js library can be generated // Take this into consideration when providing the instructions for the graph data
+- All types of graphs (using d3.js library) can be generated // Take this into consideration when providing the instructions for the graph data
 - do not make mention in the report to "graph placeholders" just mention graph.
-- in the placeholder, no need to add the references to the source, but make sure ALL of the data points required has a source from the learning and reference material hereafter 
+- in the placeholder, no need to add the references to the source or its ref number, but make sure ALL of the data points required has a source from the learning and reference material hereafter 
 - these placeholders text should contain:
     o the purpose of the future graph 
     o the relevant data to generate it
-    o the guidance in terms of look&feel (ex: red colors, bar chart style)
-    note: Be specific if you want some particular color used, keep it consistent across the report.
-- there should be at least {round(pages/4,0)} of these graphs placeholders within the report
-- 2 graph placeholders cannot be in the same or in 2 consecutive sections
-Note: the placeholders will then be processed separtely by a llm to generate the specific code to display each of them so the instruction need to be clear enough.
+- there should be at least {round(pages/4,0)} of these graphs placeholders within the report (all between introduction and conclusion)
+- 2 graph placeholders cannot be in the same section 
+Note: the placeholders will then be processed separately by a llm to generate the specific code to display each of them so the instruction need to be clear enough.
 
 // Focus placeholders
 - To drill down on specific topic that would be deserve to be developped extensively separately, create special focus placeholders in [[...]] double backets
@@ -802,12 +789,12 @@ Note: outside of the placeholder, do not make reference in the report to "focus
 - these placeholders text should contain:
     o the purpose of the focus box 
     o the relevant data to generate it
-    o the guidance in terms of style and message to conver
-    note: Be specific if you want some particular point developped, keep it consistent across the report.
-- there should be {round(pages/6,0)} of these focus placeholders within the report
-- 2 focus placeholders cannot be in the same or in 2 consecutive sections
-- Keep the placeholders for sections that cannot be developped so that you can focus on others.
-Note: the placeholders will then be processed separtely by a llm to generate the specific code to display each of them so the instruction need to be clear enough.
+    o the guidance in terms of style and message to convey
+    Note: Be specific if you want some particular point developped, keep it consistent across the report.
+- there should be {round(pages/6,0)} of these focus placeholders within the report (all between introduction and conclusion)
+- 2 focus placeholders cannot be in the same section
+- Tip: Use the placeholders for topics that cannot be developped but could be developped later independently, so that you can focus on others.
+Note: the placeholders will then be processed separately by a llm to generate the specific code to display each of them so the instruction need to be clear enough.
 
 // Format:
 [[Focus Placeholder n:
@@ -823,10 +810,10 @@ Important: after [[ put "Focus Placeholder n:" explicitly (with n as the ref num
 - Abstract
 - Table of contents (do not mention the pages)
 - Introduction
-- [Sections and sub-sections, depending on the size and relevant topic - including visual and focus placeholders]
+- [Sections and sub-sections, depending on the size and relevant topic - including visual, graph and focus placeholders]
 - Conclusion
 - References of the documents used in the inline citations
-Important: placeholders (visual, graph or focus) can only appear in the sections or sub-sections not in introduction, the conclusion, the references or after the teferences
+Important: placeholders (visual, graph or focus) can only appear in the sections or sub-sections not in introduction, the conclusion, the references or after the references
 
 Output the report directly without any introductory meta comments.