update Snowflake setup README with step-by-step production guide #149
Conversation
Jayaram007
force-pushed
the
snowflake
branch
7 times, most recently
from
8450ab6 to
723eae3
Compare
There was a problem hiding this comment.
Pull request overview
This PR updates the Snowflake setup with a comprehensive production deployment guide for AIFAQ Pro version 2. It introduces detailed configuration files and step-by-step instructions for deploying a Snowflake Native App with AI-powered FAQ capabilities.
Key changes:
- Added Snowflake deployment configuration (snowflake.yml, setup.sql, manifest.yml, environment.yml)
- Created extensive 470-line deployment and user guide
- Updated main README with improved architecture overview and folder structure descriptions
Reviewed changes
Copilot reviewed 78 out of 102 changed files in this pull request and generated 13 comments.
Show a summary per file
| File | Description |
|---|---|
| version_2/snowflake.yml | Snowflake Native App configuration defining package, application, artifacts, and deployment settings |
| version_2/setup.sql | Database schema initialization script creating tables, stages, indexes, and access controls |
| version_2/manifest.yml | Application metadata including privileges, resources, and marketplace configuration |
| version_2/environment.yml | Conda environment specification with Python dependencies for Snowflake execution |
| version_2/readme.md | Comprehensive deployment guide covering three deployment methods, troubleshooting, and marketplace publishing |
| README.md | Updated main documentation with refined architecture description and folder structure |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| Route queries to Snowflake Cortex or external OpenSource LLM models through secure external functions. | ||
|
|
||
| - **Multi-Document Knowledge Retrieval** | ||
| Supports structred and unstructred data. |
There was a problem hiding this comment.
Typo: "structred" should be "structured".
| Supports structred and unstructred data. | |
| Supports structured and unstructured data. |
| Route queries to Snowflake Cortex or external OpenSource LLM models through secure external functions. | ||
|
|
||
| - **Multi-Document Knowledge Retrieval** | ||
| Supports structred and unstructred data. |
There was a problem hiding this comment.
Typo: "unstructred" should be "unstructured".
| Supports structred and unstructred data. | |
| Supports structured and unstructured data. |
| ## Folder Descriptions | ||
|
|
||
| ### `version_1/` | ||
| A simplified demonstration build intended for quick snowflake evaluation adn to get hands on for beginners. |
There was a problem hiding this comment.
Typo: "adn" should be "and".
| A simplified demonstration build intended for quick snowflake evaluation adn to get hands on for beginners. | |
| A simplified demonstration build intended for quick snowflake evaluation and to get hands on for beginners. |
| #### Step 3: Deploy Application | ||
| ```bash | ||
| # Navigate to project folder | ||
| cd project folder |
There was a problem hiding this comment.
The instructions refer to "project folder" without specifying which directory. Users need clear guidance on which directory to navigate to (likely version_2/ based on context). Consider changing this to "cd version_2" or being more explicit about the path.
| default_role: accountadmin | ||
|
|
||
| # Project structure | ||
| definition_version: "1" No newline at end of file |
There was a problem hiding this comment.
The definition_version field is declared twice in this file - once at line 1 and again at line 44. This duplicate declaration should be removed as it can cause configuration parsing errors.
| @@ -0,0 +1,1008 @@ | |||
| import streamlit as st | |||
| from snowflake.snowpark.context import get_active_session | |||
| import uuid, re, datetime as dt | |||
There was a problem hiding this comment.
Import of 're' is not used.
| from snowflake.snowpark.context import get_active_session | ||
| import uuid, re, datetime as dt | ||
| import pandas as pd | ||
| import io |
There was a problem hiding this comment.
Import of 'io' is not used.
| """Get user documents""" | ||
| try: | ||
| return session.sql(f"SELECT DOC_ID, FILENAME, FILE_TYPE, FILE_SIZE, UPLOADED_AT FROM {DOCS_TBL} ORDER BY UPLOADED_AT DESC").to_pandas() | ||
| except: |
There was a problem hiding this comment.
Except block directly handles BaseException.
| messages.append({"role": "user", "content": r["QUERY_TEXT"]}) | ||
| messages.append({"role": "assistant", "content": r["RESPONSE_TEXT"]}) | ||
| return messages | ||
| except: |
There was a problem hiding this comment.
Except block directly handles BaseException.
| "messages": loaded_messages | ||
| } | ||
| st.rerun() | ||
| except Exception: |
There was a problem hiding this comment.
'except' clause does nothing but pass and there is no explanatory comment.
Signed-off-by: Jayaram007 <jairam.kumar23@gmail.com>
Signed-off-by: Jayaram007 <jairam.kumar23@gmail.com>
Signed-off-by: Jayaram007 <jairam.kumar23@gmail.com>
|
Merged thank you Jayaram! |
2 participants
-Added detailed instructions for implementing Snowflake setup