```python
import json
import re
from pathlib import Path
def parse_markdown_to_sidebar(markdown_content):
lines = markdown_content.splitlines()
sidebar = []
current_category = None
current_subcategory = None
for line in lines:
if line.startswith('### '):
# Subcategory
if current_subcategory is not None:
current_category['items'].append(current_subcategory)
subcategory_title = line.strip('# ').strip()
current_subcategory = {
"type": "category",
"label": subcategory_title,
"collapsed": True,
"items": [],
"link": {"type": "generated-index"}
}
elif line.startswith('## '):
# Category
if current_category is not None:
if current_subcategory is not None:
current_category['items'].append(current_subcategory)
current_subcategory = None
sidebar.append(current_category)
category_title = line.strip('# ').strip()
current_category = {
"type": "category",
"label": category_title,
"collapsed": True,
"items": [],
"link": {"type": "generated-index"}
}
elif line.startswith('- ['):
# Link
match = re.match(r'- \[(.*?)\]\((.*?)\)', line)
if match:
title, link = match.groups()
link = link.replace('/docs/', '') # Remove '/docs/' prefix
if current_subcategory is not None:
current_subcategory['items'].append(link)
elif current_category is not None:
current_category['items'].append(link)
# Add the last category and subcategory if they exist
if current_subcategory is not None:
current_category['items'].append(current_subcategory)
if current_category is not None:
sidebar.append(current_category)
return sidebar
def generate_sidebar_json(file_path):
with open(file_path, 'r') as md_file:
markdown_content = md_file.read()
sidebar = parse_markdown_to_sidebar(markdown_content)
sidebar_json = json.dumps({"items": sidebar}, indent=2)
return sidebar_json
```
Proposing to centralize code for handling dynamic imports. This allows treating langchain-community as an optional dependency.
---
The proposal is to scan the code base and to replace all existing imports with dynamic imports using this functionality.
Fixed the error that the model name is never actually put into GigaChat
request payload, always defaulting to `GigaChat-Lite`.
With this fix, model selection through
```python
import os
from langchain.chat_models.gigachat import GigaChat
chat = GigaChat(
name="GigaChat-Pro", # <- HERE!!!!!
...
)
```
should actually work, as intended in
[here](804390ba4b/libs/community/langchain_community/llms/gigachat.py (L36)).
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
**Description**: ToolKit and Tools for accessing data in a Cassandra
Database primarily for Agent integration. Initially, this includes the
following tools:
- `cassandra_db_schema` Gathers all schema information for the connected
database or a specific schema. Critical for the agent when determining
actions.
- `cassandra_db_select_table_data` Selects data from a specific keyspace
and table. The agent can pass paramaters for a predicate and limits on
the number of returned records.
- `cassandra_db_query` Expiriemental alternative to
`cassandra_db_select_table_data` which takes a query string completely
formed by the agent instead of parameters. May be removed in future
versions.
Includes unit test and two notebooks to demonstrate usage.
**Dependencies**: cassio
**Twitter handle**: @PatrickMcFadin
---------
Co-authored-by: Phil Miesle <phil.miesle@datastax.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
