From 2b87e330b0a85ebc2b3dba082a35105fe07a29df Mon Sep 17 00:00:00 2001
From: RUO <61719257+comsa33@users.noreply.github.com>
Date: Tue, 25 Jun 2024 04:29:11 +0900
Subject: [PATCH] community: fix issue with nested field extraction in
 MongodbLoader (#22801)

**Description:**
This PR addresses an issue in the `MongodbLoader` where nested fields
were not being correctly extracted. The loader now correctly handles
nested fields specified in the `field_names` parameter.

**Issue:**
Fixes an issue where attempting to extract nested fields from MongoDB
documents resulted in `KeyError`.

**Dependencies:**
No new dependencies are required for this change.

**Twitter handle:**
(Optional, your Twitter handle if you'd like a mention when the PR is
announced)

### Changes
1. **Field Name Parsing**:
- Added logic to parse nested field names and safely extract their
values from the MongoDB documents.

2. **Projection Construction**:
- Updated the projection dictionary to include nested fields correctly.

3. **Field Extraction**:
- Updated the `aload` method to handle nested field extraction using a
recursive approach to traverse the nested dictionaries.

### Example Usage
Updated usage example to demonstrate how to specify nested fields in the
`field_names` parameter:

```python
loader = MongodbLoader(
    connection_string=MONGO_URI,
    db_name=MONGO_DB,
    collection_name=MONGO_COLLECTION,
    filter_criteria={"data.job.company.industry_name": "IT", "data.job.detail": { "$exists": True }},
    field_names=[
        "data.job.detail.id",
        "data.job.detail.position",
        "data.job.detail.intro",
        "data.job.detail.main_tasks",
        "data.job.detail.requirements",
        "data.job.detail.preferred_points",
        "data.job.detail.benefits",
    ],
)

docs = loader.load()
print(len(docs))
for doc in docs:
    print(doc.page_content)
```
### Testing
Tested with a MongoDB collection containing nested documents to ensure
that the nested fields are correctly extracted and concatenated into a
single page_content string.
### Note
This change ensures backward compatibility for non-nested fields and
improves functionality for nested field extraction.
### Output Sample
```python
print(docs[:3])
```
```shell
# output sample:
[
    Document(
        # Here in this example, page_content is the combined text from the fields below
        # "position", "intro", "main_tasks", "requirements", "preferred_points", "benefits"
        page_content='all combined contents from the requested fields in the document',
        metadata={'database': 'Your Database name', 'collection': 'Your Collection name'}
    ),
    ...
]
```

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
---
 .../document_loaders/mongodb.py                    | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/libs/community/langchain_community/document_loaders/mongodb.py b/libs/community/langchain_community/document_loaders/mongodb.py
index 57b4f35217..b1e0622265 100644
--- a/libs/community/langchain_community/document_loaders/mongodb.py
+++ b/libs/community/langchain_community/document_loaders/mongodb.py
@@ -77,7 +77,19 @@ class MongodbLoader(BaseLoader):
 
             # Extract text content from filtered fields or use the entire document
             if self.field_names is not None:
-                fields = {name: doc[name] for name in self.field_names}
+                fields = {}
+                for name in self.field_names:
+                    # Split the field names to handle nested fields
+                    keys = name.split(".")
+                    value = doc
+                    for key in keys:
+                        if key in value:
+                            value = value[key]
+                        else:
+                            value = ""
+                            break
+                    fields[name] = value
+
                 texts = [str(value) for value in fields.values()]
                 text = " ".join(texts)
             else: