themefinder 0.7.0__py3-none-any.whl → 0.7.1__py3-none-any.whl

themefinder/prompts/detail_detection.txt

@@ -4,11 +4,23 @@ You will receive a list of RESPONSES, each containing a response_id and a respon
 Your job is to analyze each response to the QUESTION below and decide if a response contains rich evidence.
 You MUST include every response ID in the output.
 
-Evidence-rich responses contain one or more of the following:
-- Specific facts or figures that shed new light on the issue (e.g., statistics, percentages, measurements, dates)
-- Concrete examples and specific insights that could inform decision-making
-- Detailed personal or professional experiences with clear contextual information or specific incidents
-In addition to the above an evidence rich response should answer the question and provide deeper insights than an average response.
+A response is evidence-rich only if it satisfies both of the following:
+
+Relevance and depth:
+    - It clearly answers the question
+    - AND provides insights that go beyond generic opinion, such as nuanced reasoning, contextual explanation, or argumentation that could inform decision-making
+
+Substantive evidence, including at least one of:
+    - Specific, verifiable facts or data (e.g., statistics, dates, named reports or studies)
+    - Concrete, illustrative examples that clearly support a broader claim
+    - Detailed personal or professional experiences that include contextual information (e.g., roles, locations, timelines)
+
+Do NOT classify a response as evidence-rich if it:
+    - Uses vague or general language with no supporting detail
+    - Restates commonly known points without adding new information
+    - Shares personal anecdotes without sufficient context or a clear takeaway
+
+Before answering, ask: Would this response provide useful input to someone drafting policy, beyond what is already commonly known or expected?
 
 For each response, determine:
 EVIDENCE_RICH - does the response contain significant evidence as defined above?

{themefinder-0.7.0.dist-info → themefinder-0.7.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: themefinder
-Version: 0.7.0
+Version: 0.7.1
 Summary: A topic modelling Python package designed for analysing one-to-many question-answer data eg free-text survey responses.
 License: MIT
 Author: i.AI
@@ -17,7 +17,7 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Text Processing :: Linguistic
 Requires-Dist: boto3 (>=1.29,<2.0)
 Requires-Dist: langchain
-Requires-Dist: langchain-openai (==0.1.17)
+Requires-Dist: langchain-openai
 Requires-Dist: langfuse (==2.29.1)
 Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
 Requires-Dist: pandas (>=2.2.2,<3.0.0)

{themefinder-0.7.0.dist-info → themefinder-0.7.1.dist-info}/RECORD

@@ -4,7 +4,7 @@ themefinder/llm_batch_processor.py,sha256=Z9jm9Kr-6GD8g8kLkgdW97onjUbLLQ2M1YKwok
 themefinder/models.py,sha256=JopmD4F23Mteh60m6WDpsuTs58dRc0tUbVX-d-L8Gv8,14680
 themefinder/prompts/agentic_theme_clustering.txt,sha256=6bHLpgZUQEaZXpLUB7EcMEbtXGqQ_1yniqZ6ZBJHFn0,1917
 themefinder/prompts/consultation_system_prompt.txt,sha256=_A07oY_an4hnRx-9pQ0y-TLXJz0dd8vDI-MZne7Mdb4,89
-themefinder/prompts/detail_detection.txt,sha256=6Vr_oN7rF5BCFipnCIHTSF8MmjerGyCixRWRT3vni1U,941
+themefinder/prompts/detail_detection.txt,sha256=hMB8yQR5y855TJLYSW3CNZDkLTPaA2lf9UJwH_GpkD4,1515
 themefinder/prompts/sentiment_analysis.txt,sha256=vYCDhtEsG5I9xixwVhZbvKPJGU1Gqpw4-xAqGz72xhU,1671
 themefinder/prompts/theme_condensation.txt,sha256=pHWuCtfU58gdtP2BfGZWOTvcb0MnTpb9OhOCGtkJv8U,1672
 themefinder/prompts/theme_generation.txt,sha256=QRKW7DtcMSb2olT6j5jmdEPcXPMeZgogM-NYddEIKRk,1871
@@ -13,7 +13,7 @@ themefinder/prompts/theme_refinement.txt,sha256=evWMCIEdeZCJ8zn4SBNgP6bmfAb0vzKi
 themefinder/prompts/theme_target_alignment.txt,sha256=g7AVZLiP_xIH010X5SIZyG3q7gA6OBAplPv3xvmstOY,855
 themefinder/theme_clustering_agent.py,sha256=Ie-5MFvIo7ukeeDXNpLawJXqLqBb6kvUGgSH6uTGL20,12826
 themefinder/themefinder_logging.py,sha256=n5SUQovEZLC4skEbxicjz_fOGF9mOk3S-Wpj5uXsaL8,314
-themefinder-0.7.0.dist-info/LICENCE,sha256=C9ULIN0ctF60ZxUWH_hw1H434bDLg49Z-Qzn6BUHgqs,1060
-themefinder-0.7.0.dist-info/METADATA,sha256=-PRjz0RTxp-yJsuavj8tw5NwtC1amsw12JyKNOitxZw,6737
-themefinder-0.7.0.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-themefinder-0.7.0.dist-info/RECORD,,
+themefinder-0.7.1.dist-info/LICENCE,sha256=C9ULIN0ctF60ZxUWH_hw1H434bDLg49Z-Qzn6BUHgqs,1060
+themefinder-0.7.1.dist-info/METADATA,sha256=1PHpWby6fNMmSyo1TLnGn2zkT6qN60osdJ3Q0AO0nW8,6726
+themefinder-0.7.1.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+themefinder-0.7.1.dist-info/RECORD,,