14 missing content (#16)

* refactor: prompt flex to different keywords

* refactor: add name placeholder but no speaker assigned

* refactor: add model name to report

src/parliai_public/_config/debates.toml

@@ -12,10 +12,10 @@ prompt = """
 You are a skim reader, specialising in capturing the key points in
 frenetic parliamentary debate.
 Using only the text provided, you will extract ONLY sentences verbatim
-which exactly match to any of these {keywords}.
+which exactly reference {keywords}. You may include sentences before and/or after
+that provide useful and relevant context.
 Do not paraphrase.
 Do not return any answer or message if there isn't anything relevant in the text.
-Do not include any political asides which do not reference any of these {keywords}.
 
 Now extract all relevant content from the following text:
 

src/parliai_public/_config/wrans.toml

@@ -4,10 +4,10 @@ prompt = """
 You are a skim reader, specialising in capturing the key points in
 written parliamentary communications.
 Using only the text provided, you will extract ONLY sentences verbatim
-which exactly match to any of these {keywords}.
+which exactly reference {keywords}. You may include sentences before and/or after
+that provide useful and relevant context.
 Do not paraphrase.
 Do not return any answer or message if there isn't anything relevant in the text.
-Do not include any political asides which do not reference any of these {keywords}.
 
 Now extract all relevant content from the following text:
 

src/parliai_public/readers/base.py

@@ -547,6 +547,7 @@ def make_header(self, urls: list[str] = None) -> str:
                 f"Publication date: {today}",
                 f"Period covered: {period}",
                 f"Search terms: {self.terms}",
+                f"Model used: {self.llm_name}",
                 "\n".join((source, *links)),
             )
         )

src/parliai_public/readers/theyworkforyou.py

@@ -382,12 +382,21 @@ def render(self, transcript: dict) -> str:
         title = f"## {label}: [{transcript['title']}]({transcript['url']})"
         processed = []
         for speech in transcript["speeches"]:
-            if speech["name"] and "response" in speech:
-                speaker = (
-                    f"### [{speech['name']}]({speech['url']})"
-                    f" ({speech['position']})"
-                )
-                processed.append("\n\n".join((speaker, speech["response"])))
+            if "response" in speech:
+                if speech["name"]:
+                    speaker = (
+                        f"### [{speech['name']}]({speech['url']})"
+                        f" ({speech['position']})"
+                    )
+                    processed.append(
+                        "\n\n".join((speaker, speech["response"]))
+                    )
+                else:
+                    # if no speaker, return placeholder and response
+                    speaker = "### No speaker assigned"
+                    processed.append(
+                        "\n\n".join((speaker, speech["response"]))
+                    )
 
         return "\n\n".join((title, *processed))