From ce914b396a05b2de19d96a6725b51db547962de0 Mon Sep 17 00:00:00 2001
From: Sameer6305 <sskadam6305@gmail.com>
Date: Tue, 28 Jul 2026 15:00:02 +0530
Subject: [PATCH] docs: clarify Snowflake OAuth auth, add ArrowIngestor and
 non-re-exported ingestors (PR #808)

---
 README.md                | 6 ++++--
 docs/guides/ingest.md    | 4 +++-
 docs/reference/ingest.md | 1 +
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 0c65ca32..08580cd4 100644
--- a/README.md
+++ b/README.md
@@ -382,16 +382,18 @@ table_lineage = databricks.get_table_lineage("customers", catalog="main", schema
 snowflake = SnowflakeIngestor(
     account="myaccount",
     user="myuser",
-    password="mypassword",              # or private_key / token for key-pair / OAuth auth
+    password="mypassword",              # or private_key=... for key-pair; use authenticator="oauth", token=... for OAuth
     warehouse="COMPUTE_WH",
     database="MYDB",
 )
 orders = snowflake.ingest_table("ORDERS", limit=10_000)
 ```
 
+> **Security Note:** Never hardcode credentials (`token`, `password`, `private_key`) in production code; pass them via environment variables (e.g., `DATABRICKS_TOKEN`, `SNOWFLAKE_PASSWORD`) or a secrets manager.
+
 **Supported sources:** Local files (PDF, DOCX, PPTX, HTML, TXT, CSV, JSON, YAML, Excel, XML) · Web pages · RSS/Atom feeds · REST APIs · Databases (PostgreSQL, MySQL, SQLite, Oracle, SQL Server) · Parquet datasets · Databricks (Unity Catalog + Delta Lake) · Snowflake · Git repositories · Email (IMAP/POP3) · Message streams (Kafka, RabbitMQ, Kinesis, Pulsar) · MCP resources · Apache Arrow/Feather/IPC (`ArrowIngestor`)
 
-Elasticsearch and Google Drive ingestion also ship (`ElasticIngestor`, `GDriveIngestor`) but aren't re-exported from the top-level `semantica.ingest` namespace yet — import them directly: `from semantica.ingest.elastic_ingestor import ElasticIngestor`.
+DuckDB, Elasticsearch, Google Drive, HuggingFace, MongoDB, and Pandas ingestion also ship (`DuckDBIngestor`, `ElasticIngestor`, `GDriveIngestor`, `HuggingFaceIngestor`, `MongoIngestor`, `PandasIngestor`) but aren't re-exported from the top-level `semantica.ingest` namespace yet — import them directly: `from semantica.ingest.duckdb_ingestor import DuckDBIngestor`.
 
 </details>
 
diff --git a/docs/guides/ingest.md b/docs/guides/ingest.md
index 76836cce..dd4297a6 100644
--- a/docs/guides/ingest.md
+++ b/docs/guides/ingest.md
@@ -340,7 +340,7 @@ from semantica.ingest import SnowflakeIngestor
 snowflake = SnowflakeIngestor(
     account="myaccount",
     user="myuser",
-    password="mypassword",         # or private_key / token for key-pair / OAuth auth
+    password="mypassword",         # or private_key=... for key-pair; use authenticator="oauth", token=... for OAuth
     warehouse="COMPUTE_WH",
     database="ANALYTICS",
     schema="PUBLIC",
@@ -380,6 +380,8 @@ print(f"Enterprise data graph: {graph.stats()['node_count']} nodes")
 
 For authentication details (PAT vs. OAuth M2M for Databricks; password vs. key-pair vs. OAuth for Snowflake), schema/catalog introspection, and troubleshooting, see the dedicated [Databricks Integration](../integrations/databricks) and [Snowflake Integration](../integrations/snowflake) guides.
 
+> **Security Note:** Never hardcode credentials (`token`, `password`, `private_key`) in production code; pass them via environment variables (e.g., `DATABRICKS_TOKEN`, `SNOWFLAKE_PASSWORD`) or a secrets manager.
+
 ## Combining All Five Sources
 
 Once you have text from each source, `AgentContext.store()` accepts a flat list of strings. Semantica embeds and indexes them together — the context graph has no concept of which string came from which source unless you add metadata explicitly.
diff --git a/docs/reference/ingest.md b/docs/reference/ingest.md
index 99eef7b2..b6d16eae 100644
--- a/docs/reference/ingest.md
+++ b/docs/reference/ingest.md
@@ -29,6 +29,7 @@ icon: "database"
 | `SnowflakeIngestor` | Snowflake data warehouse queries and table exports |
 | `DatabricksIngestor` | Databricks Unity Catalog metadata, Delta table queries, and lineage |
 | `ParquetIngestor` | Apache Parquet files and partitioned datasets with column selection |
+| `ArrowIngestor` | Apache Arrow IPC and Feather file processing |
 | `XMLIngestor` | XXE-safe XML parsing with optional XSD schema validation |
 | `EmailIngestor` | IMAP/POP3 email ingestion with attachment extraction |
 | `OntologyIngestor` | OWL/RDF/Turtle ontology file ingestion |