Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature: Conditional input interview transcript #62

Open
wants to merge 25 commits into
base: feature/speaker_diarization
Choose a base branch
from

Conversation

Abhishek-Jain-1925
Copy link
Contributor

Workdone is as follows -

  1. Conditionally accepting Transcript File and Transcript File URL for ArCruit Result Generation

Copy link
Contributor

@AjinkyaASK AjinkyaASK left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Requested suggestions and changes inline.

@@ -0,0 +1,37 @@
CREATE TABLE IF NOT EXISTS "analysis_feedback" (
"id" text PRIMARY KEY NOT NULL,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why primary key id is of type text?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

As we are storing the IDs in AlphaNumeric Format so that type text is used

@@ -0,0 +1,37 @@
CREATE TABLE IF NOT EXISTS "analysis_feedback" (
"id" text PRIMARY KEY NOT NULL,
"user_id" text NOT NULL,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why foreign key user_id is of type text?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

As we are storing the IDs in AlphaNumeric Format so that type text is used

"user_id" text NOT NULL,
"analysis_id" uuid NOT NULL,
"is_found_useful" boolean NOT NULL,
"impact" text,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What's column 'impact' here?
Is this field where we store feedback messages? If yes please name it accordingly.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done!

"parsed_job_description" text,
"analysis_result" text,
"conversation" text,
"status" text,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we convert 'status' to enum?

"analysis_result" text,
"conversation" text,
"status" text,
"created_at" timestamp DEFAULT now()
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We're missing 'updated_at' column.

<FormControl>
<Input
type="file"
accept=".txt,.docx,.pdf"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does our code support reading from all these file types?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

As per instructions it only accepting .txt,.docx,.pdf files


def get_question_level_ratings(Asked_Questions):
try:
file_path = "/Users/sethupathiasokan/Documents/AiCruit/lingo.ai/Scorecard Template.xlsx"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why is this hardcoded path there?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Currently we are using excel file here to get question bank later we are going to integrate database.
So for now, will add this path in the .env file

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added path in a .env file

def get_question_level_ratings(Asked_Questions):
try:
file_path = "/Users/sethupathiasokan/Documents/AiCruit/lingo.ai/Scorecard Template.xlsx"
sheet_name = "Java"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this still under development?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Currently we are using excel file here to get question bank later we are going to integrate database. Will add this path in .env file

# Perform transcription and speaker diarization
transcription_result = transcription_with_speaker_diarization(request)
transcript = transcription_result["transcript"]
questions_answers = transcription_result["qna"]
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This if-else ladder can be optimized.

For example, This line is repeated 3 times:
questions_answers = transcription_result["qna"]

This method is called three times:
extract_conversation_from_file

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Need to rewrite the 'QNA_DIFFCULTY_LEVEL_RATING_FIND_PROMPT' prompt, as discussed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants