Spaces:
Running
on
Zero
Running
on
Zero
seanpedrickcase
commited on
Commit
·
f0b3bbc
1
Parent(s):
f5a842c
Updated intro and readme to link to datasets
Browse files
README.md
CHANGED
@@ -13,7 +13,9 @@ license: cc-by-nc-4.0
|
|
13 |
|
14 |
Extract topics and summarise outputs using Large Language Models (LLMs, Gemma 2b instruct if local, Gemini Flash/Pro, or Claude 3 through AWS Bedrock if running on AWS). The app will query the LLM with batches of responses to produce summary tables, which are then compared iteratively to output a table with the general topics, subtopics, topic sentiment, and relevant text rows related to them. The prompts are designed for topic modelling public consultations, but they can be adapted to different contexts (see the LLM settings tab to modify).
|
15 |
|
16 |
-
|
|
|
|
|
17 |
|
18 |
NOTE: that **API calls to Gemini are not considered secure**, so please only submit redacted, non-sensitive tabular files to this source. Also, large language models are not 100% accurate and may produce biased or harmful outputs. All outputs from this app **absolutely need to be checked by a human** to check for harmful outputs, hallucinations, and accuracy.
|
19 |
|
|
|
13 |
|
14 |
Extract topics and summarise outputs using Large Language Models (LLMs, Gemma 2b instruct if local, Gemini Flash/Pro, or Claude 3 through AWS Bedrock if running on AWS). The app will query the LLM with batches of responses to produce summary tables, which are then compared iteratively to output a table with the general topics, subtopics, topic sentiment, and relevant text rows related to them. The prompts are designed for topic modelling public consultations, but they can be adapted to different contexts (see the LLM settings tab to modify).
|
15 |
|
16 |
+
Try it out with this [dummy development consultation dataset](https://huggingface.co/datasets/seanpedrickcase/dummy_development_consultation), which you can also try with [zero-shot topics](https://huggingface.co/datasets/seanpedrickcase/dummy_development_consultation/blob/main/example_zero_shot.csv), or this [dummy case notes dataset](https://huggingface.co/datasets/seanpedrickcase/dummy_case_notes).
|
17 |
+
|
18 |
+
You can use an AWS Bedrock model (Claude 3, paid), or Gemini (a free API, but with strict limits for the Pro model). Due to the strict API limits for the best model (Pro 1.5), the use of Gemini requires an API key. To set up your own Gemini API key, go [here](https://aistudio.google.com/app/u/1/plan_information).
|
19 |
|
20 |
NOTE: that **API calls to Gemini are not considered secure**, so please only submit redacted, non-sensitive tabular files to this source. Also, large language models are not 100% accurate and may produce biased or harmful outputs. All outputs from this app **absolutely need to be checked by a human** to check for harmful outputs, hallucinations, and accuracy.
|
21 |
|
app.py
CHANGED
@@ -81,9 +81,11 @@ with app:
|
|
81 |
gr.Markdown(
|
82 |
"""# Large language model topic modelling
|
83 |
|
84 |
-
Extract topics and summarise outputs using Large Language Models (LLMs, Gemma
|
|
|
|
|
85 |
|
86 |
-
You can use an AWS Bedrock model (Claude 3, paid), or Gemini (a free API, but with strict limits for the Pro model). Due to the strict API limits for the best model (Pro 1.5), the use of Gemini requires an API key. To set up your own Gemini API key, go here
|
87 |
|
88 |
NOTE: that **API calls to Gemini are not considered secure**, so please only submit redacted, non-sensitive tabular files to this source. Also, large language models are not 100% accurate and may produce biased or harmful outputs. All outputs from this app **absolutely need to be checked by a human** to check for harmful outputs, hallucinations, and accuracy.""")
|
89 |
|
|
|
81 |
gr.Markdown(
|
82 |
"""# Large language model topic modelling
|
83 |
|
84 |
+
Extract topics and summarise outputs using Large Language Models (LLMs, Gemma 2B instruct if local, Gemini Flash/Pro, or Claude 3 through AWS Bedrock if running on AWS). The app will query the LLM with batches of responses to produce summary tables, which are then compared iteratively to output a table with the general topics, subtopics, topic sentiment, and relevant text rows related to them. The prompts are designed for topic modelling public consultations, but they can be adapted to different contexts (see the LLM settings tab to modify).
|
85 |
+
|
86 |
+
Instructions on use can be found in the README.md file. Try it out with this [dummy development consultation dataset](https://huggingface.co/datasets/seanpedrickcase/dummy_development_consultation), which you can also try with [zero-shot topics](https://huggingface.co/datasets/seanpedrickcase/dummy_development_consultation/blob/main/example_zero_shot.csv), or this [dummy case notes dataset](https://huggingface.co/datasets/seanpedrickcase/dummy_case_notes).
|
87 |
|
88 |
+
You can use an AWS Bedrock model (Claude 3, paid), or Gemini (a free API, but with strict limits for the Pro model). Due to the strict API limits for the best model (Pro 1.5), the use of Gemini requires an API key. To set up your own Gemini API key, go [here](https://aistudio.google.com/app/u/1/plan_information).
|
89 |
|
90 |
NOTE: that **API calls to Gemini are not considered secure**, so please only submit redacted, non-sensitive tabular files to this source. Also, large language models are not 100% accurate and may produce biased or harmful outputs. All outputs from this app **absolutely need to be checked by a human** to check for harmful outputs, hallucinations, and accuracy.""")
|
91 |
|