# AI Employee - Knowledge Base Tables > Add tables to your GHL Customer Care Knowledge Base for AI employees to pick key columns, upload CSVs, and keep working while indexing finishes in the background. - Source: https://docs.ghlcustomercare.com/docs/ai-employee/knowledge-bases/ai-employee-knowledge-base-tables - Section: AI Employee / Knowledge Bases - Reading time: 3 min - Images: 8, each explained below - Modified on Thu, 29 Jan at 1:22 PM --- Give your AI Agents instant access to tables! Table Search in GHL Customer Care Knowledge Base lets you upload CSV files and query them with natural-language questions, turning static rows of data into dynamic knowledge your bots can use during conversations. --- **TABLE OF CONTENTS** - [What is Table Search in Knowledge Base?](#what-is-table-search-in-knowledge-base)[](#key-benefits-of-table-search-in-knowledge-base) - [Key Benefits of Table Search in Knowledge Base](#key-benefits-of-table-search-in-knowledge-base)[](#how-to-setup-table-search-in-knowledge-base) - [How to Setup Table Search in Knowledge Base](#how-to-setup-table-search-in-knowledge-base)[](#csv-file-requirements) - [CSV File Requirements](#csv-file-requirements)[](#semantic-search-intelligence) - [Semantic Search Intelligence](#semantic-search-intelligence)[](#smart-table-processing) - [Smart Table Processing](#smart-table-processing)[](#frequently-asked-questions) - [Frequently Asked Questions](#frequently-asked-questions)[](#related-articles) - [Related Articles](#related-articles) --- # **What is Table Search in Knowledge Base?** Table Search adds a new “**Table** **Source**” type to GHL Customer Care Knowledge Base. By ingesting CSV files (up to 50,000 rows, 500 columns and select the 20 most relevant columns), the platform semantically indexes every record so your AI bots can answer questions about customers, inventory, transactions, or any other structured data you provide. Unlike keyword search, GHL Customer Care applies semantic similarity matching, allowing users to ask plain-English questions and receive context-aware results. --- ## **Key Benefits of Table Search in Knowledge Base** - **Natural-language queries:** Ask plain-English questions on table data without formulas or filters. - **Semantic search intelligence:** Returns accurate, context-aware answers from relevant rows and columns. - **Large CSV support:** Handles up to 50,000 rows and 500 columns; select the 20 most relevant for indexing. - **Beyond web/docs:** Surfaces structured data that web pages and documents don’t capture well. - **Bot enablement:** Lets AI employees handle customer records, product catalogs, KPIs, and similar tabular use cases. --- ## **How to Setup Table Search in Knowledge Base** 1. Open **AI Agents** → **Knowledge Base**. ![Step 1 of 8: Open AI Agents → Knowledge Base](https://jumpshare.com/share/BEnlIdlnCRxrdC9eSszT+/Screen+Shot+2026-01-07+at+7.02.31+PM.png) **Step 1 of 8: Open AI Agents → Knowledge Base** This screenshot accompanies step 1 of 8 in the "How to Setup Table Search in Knowledge Base" section of "AI Employee - Knowledge Base Tables". At this point in the walkthrough you open AI Agents → Knowledge Base. For context, this section explains: Open AI Agents → Knowledge Base. Edit an existing Knowledge Base, or click Create Knowledge Base and give it a name & description. Click Add Source, then choose Table s. Upload your CSV file using drag-and-drop or file picker. (Max 50 MB). Review detected columns; adjust data types if needed…. The next step is to edit an existing Knowledge Base, or click Create Knowledge Base and give it a name & description. - Where to go: Open AI Agents → Knowledge Base. - Controls: AI Agents, Knowledge Base, Edit, existing, Knowledge, Base, Create, Add Source, Table, s, CSV, file - Next: Edit an existing Knowledge Base, or click Create Knowledge Base and give it a name & description. Full procedure: 1. Open AI Agents → Knowledge Base. <- this image 2. Edit an existing Knowledge Base, or click Create Knowledge Base and give it a name & description. 3. Click Add Source, then choose Table s. 4. Upload your CSV file using drag-and-drop or file picker. (Max 50 MB). 5. Review detected columns; adjust data types if needed. 6. Click Done to index the table. Progress shows chunking status. 7. Attach the Knowledge Base to your AI Agent (Chat, Voice, or Workflow AI) as usual. 8. Test a sample question like “Which customers have overdue invoices?” to confirm results. 2. **Edit** an **existing** **Knowledge** **Base**, or click **Create** **Knowledge** **Base** and give it a name & description. ![Step 2 of 8: Edit an existing Knowledge Base, or click Create Knowledge Base and…](https://jumpshare.com/share/kJHVNu71XsnEDwTtYtLI+/Screen+Shot+2026-01-07+at+7.04.46+PM.png) **Step 2 of 8: Edit an existing Knowledge Base, or click Create Knowledge Base and…** This screenshot accompanies step 2 of 8 in the "How to Setup Table Search in Knowledge Base" section of "AI Employee - Knowledge Base Tables". At this point in the walkthrough you edit an existing Knowledge Base, or click Create Knowledge Base and give it a name & description. The next step is to click Add Source, then choose Table s. - What to click: Edit an existing Knowledge Base, or click Create Knowledge Base and give it a name & description. - Controls: Edit, existing, Knowledge, Base, Create, AI Agents, Knowledge Base, Add Source, Table, s, CSV, file - Next: Click Add Source, then choose Table s. Full procedure: 1. Open AI Agents → Knowledge Base. 2. Edit an existing Knowledge Base, or click Create Knowledge Base and give it a name & description. <- this image 3. Click Add Source, then choose Table s. 4. Upload your CSV file using drag-and-drop or file picker. (Max 50 MB). 5. Review detected columns; adjust data types if needed. 6. Click Done to index the table. Progress shows chunking status. 7. Attach the Knowledge Base to your AI Agent (Chat, Voice, or Workflow AI) as usual. 8. Test a sample question like “Which customers have overdue invoices?” to confirm results. 3. Click **Add Source**, then choose **Table****s**. ![Step 3 of 8: Click Add Source, then choose Table s](https://jumpshare.com/share/0FWEBd3hReS7yWyJ2dQ9+/Screen+Shot+2026-01-07+at+7.05.59+PM.png) **Step 3 of 8: Click Add Source, then choose Table s** This screenshot accompanies step 3 of 8 in the "How to Setup Table Search in Knowledge Base" section of "AI Employee - Knowledge Base Tables". At this point in the walkthrough you click Add Source, then choose Table s. For context, this section explains: Open AI Agents → Knowledge Base. Edit an existing Knowledge Base, or click Create Knowledge Base and give it a name & description. Click Add Source, then choose Table s. Upload your CSV file using drag-and-drop or file picker. (Max 50 MB). Review detected columns; adjust data types if needed…. The next step is to upload your CSV file using drag-and-drop or file picker. (Max 50 MB). - What to choose: Click Add Source, then choose Table s. - Controls: Add Source, Table, s, AI Agents, Knowledge Base, Edit, existing, Knowledge, Base, Create, CSV, file - Next: Upload your CSV file using drag-and-drop or file picker. (Max 50 MB). Full procedure: 1. Open AI Agents → Knowledge Base. 2. Edit an existing Knowledge Base, or click Create Knowledge Base and give it a name & description. 3. Click Add Source, then choose Table s. <- this image 4. Upload your CSV file using drag-and-drop or file picker. (Max 50 MB). 5. Review detected columns; adjust data types if needed. 6. Click Done to index the table. Progress shows chunking status. 7. Attach the Knowledge Base to your AI Agent (Chat, Voice, or Workflow AI) as usual. 8. Test a sample question like “Which customers have overdue invoices?” to confirm results. 4. Upload your **CSV** **file** using drag-and-drop or file picker. (Max **50** **MB**). ![Step 4 of 8: Upload your CSV file using drag-and-drop or file picker. (Max 50 MB)](https://jumpshare.com/share/oKskwpnUnQiL6qZVb5km+/Screen+Shot+2026-01-07+at+7.07.14+PM.png) **Step 4 of 8: Upload your CSV file using drag-and-drop or file picker. (Max 50 MB)** This screenshot accompanies step 4 of 8 in the "How to Setup Table Search in Knowledge Base" section of "AI Employee - Knowledge Base Tables". At this point in the walkthrough you upload your CSV file using drag-and-drop or file picker. (Max 50 MB). The next step is to review detected columns; adjust data types if needed. - What this covers: Upload your CSV file using drag-and-drop or file picker. (Max 50 MB). - Controls: CSV, file, MB, AI Agents, Knowledge Base, Edit, existing, Knowledge, Base, Create, Add Source, Table - Next: Review detected columns; adjust data types if needed. Full procedure: 1. Open AI Agents → Knowledge Base. 2. Edit an existing Knowledge Base, or click Create Knowledge Base and give it a name & description. 3. Click Add Source, then choose Table s. 4. Upload your CSV file using drag-and-drop or file picker. (Max 50 MB). <- this image 5. Review detected columns; adjust data types if needed. 6. Click Done to index the table. Progress shows chunking status. 7. Attach the Knowledge Base to your AI Agent (Chat, Voice, or Workflow AI) as usual. 8. Test a sample question like “Which customers have overdue invoices?” to confirm results. 5. **Review** detected **columns**; adjust data types if needed. ![Step 5 of 8: Review detected columns; adjust data types if needed](https://jumpshare.com/share/gL8ymbdP17XBITWl1PoS+/Screen+Shot+2026-01-07+at+7.09.28+PM.png) **Step 5 of 8: Review detected columns; adjust data types if needed** This screenshot accompanies step 5 of 8 in the "How to Setup Table Search in Knowledge Base" section of "AI Employee - Knowledge Base Tables". At this point in the walkthrough you review detected columns; adjust data types if needed. The next step is to click Done to index the table. Progress shows chunking status. - What this covers: Review detected columns; adjust data types if needed. - Controls: Review, columns, AI Agents, Knowledge Base, Edit, existing, Knowledge, Base, Create, Add Source, Table, s - Next: Click Done to index the table. Progress shows chunking status. Full procedure: 1. Open AI Agents → Knowledge Base. 2. Edit an existing Knowledge Base, or click Create Knowledge Base and give it a name & description. 3. Click Add Source, then choose Table s. 4. Upload your CSV file using drag-and-drop or file picker. (Max 50 MB). 5. Review detected columns; adjust data types if needed. <- this image 6. Click Done to index the table. Progress shows chunking status. 7. Attach the Knowledge Base to your AI Agent (Chat, Voice, or Workflow AI) as usual. 8. Test a sample question like “Which customers have overdue invoices?” to confirm results. 6. Click **Done** to index the table. Progress shows chunking status. 7. Attach the Knowledge Base to your AI Agent (Chat, Voice, or Workflow AI) as usual. 8. Test a sample question like “Which customers have overdue invoices?” to confirm results. ![Step 8 of 8: Test a sample question like “Which customers have overdue invoices?”…](https://jumpshare.com/share/4MxvShbziO8Htfs2lkob+/Screen+Shot+2026-01-07+at+7.12.44+PM.png) **Step 8 of 8: Test a sample question like “Which customers have overdue invoices?”…** This screenshot accompanies step 8 of 8 in the "How to Setup Table Search in Knowledge Base" section of "AI Employee - Knowledge Base Tables". At this point in the walkthrough you test a sample question like “Which customers have overdue invoices?” to confirm results. - How to confirm: Test a sample question like “Which customers have overdue invoices?” to confirm results. - Controls: AI Agents, Knowledge Base, Edit, existing, Knowledge, Base, Create, Add Source, Table, s, CSV, file Full procedure: 1. Open AI Agents → Knowledge Base. 2. Edit an existing Knowledge Base, or click Create Knowledge Base and give it a name & description. 3. Click Add Source, then choose Table s. 4. Upload your CSV file using drag-and-drop or file picker. (Max 50 MB). 5. Review detected columns; adjust data types if needed. 6. Click Done to index the table. Progress shows chunking status. 7. Attach the Knowledge Base to your AI Agent (Chat, Voice, or Workflow AI) as usual. 8. Test a sample question like “Which customers have overdue invoices?” to confirm results. <- this image --- ## **CSV File Requirements** Understanding the file specifications ensures a flawless upload. - **Format:** **.csv** only (UTF-8 recommended) - **Size limits:** **50,000 rows** and **500 columns** per location (select the 20 most relevant columns), upload files up to **50 MB**. - **Header row:** First row must contain column names - **Data types:** Automatic schema detection with 80 % confidence threshold - **Clean data:** Remove null values, hidden formulas, merged cells, etc The CSV can be rejected at several points. For example, if the format of the CSV is accepted, the data itself might still contain an error. ![CSV File Requirements (image 7 of 8)](https://s3.amazonaws.com/cdn.freshdesk.com/data/helpdesk/attachments/production/155055756639/original/urfsUUfSsQNa9gkEA3ky9QT_lVhFQVjZzg.png) **CSV File Requirements (image 7 of 8)** This screenshot appears in the "CSV File Requirements" section of "AI Employee - Knowledge Base Tables". The text alongside this image reads: The CSV can be rejected at several points. For example, if the format of the CSV is accepted, the data itself might still contain an error. This part of the guide covers 2 fields, listed below. Immediately after, the guide continues: In this case you can inspect the CSV manually in a spreadsheet program or even a text editor. - What this covers: The CSV can be rejected at several points. For example, if the format of the CSV is accepted, the data itself might still contain an error. - Fields: Format:.csv only (UTF-8 recommended), Header row: First row must contain column names - Controls: .csv, 50,000 rows, 500 columns, 50 MB - Next: In this case you can inspect the CSV manually in a spreadsheet program or even a text editor. Full procedure: 1. Format:.csv only (UTF-8 recommended) 2. Size limits: 50,000 rows and 500 columns per location (select the 20 most relevant columns), upload files up to 50 MB. 3. Header row: First row must contain column names 4. Data types: Automatic schema detection with 80 % confidence threshold 5. Clean data: Remove null values, hidden formulas, merged cells, etc In this case you can inspect the CSV manually in a spreadsheet program or even a text editor. ![CSV File Requirements (image 8 of 8)](https://s3.amazonaws.com/cdn.freshdesk.com/data/helpdesk/attachments/production/155055756630/original/9pUQ1ro4k9ZiwjCvuA_OWRJEXhN18INQZw.png) **CSV File Requirements (image 8 of 8)** This screenshot appears in the "CSV File Requirements" section of "AI Employee - Knowledge Base Tables". The text alongside this image reads: In this case you can inspect the CSV manually in a spreadsheet program or even a text editor. This part of the guide covers 2 fields, listed below. Immediately after, the guide continues: GHL Customer Care converts each table row into vector embeddings so the bot can “understand” meanings rather than exact words. This enables queries like “Show me customers who complained about billing” or “Which orders shipped overnight…. - What this covers: In this case you can inspect the CSV manually in a spreadsheet program or even a text editor. - Fields: Format:.csv only (UTF-8 recommended), Header row: First row must contain column names - Controls: .csv, 50,000 rows, 500 columns, 50 MB - Next: GHL Customer Care converts each table row into vector embeddings so the bot can “understand” meanings rather than exact words. This enables queries like “Show me customers who complained about billing” or “Which orders shipped overnight last week?” The engine compares the user’s question to every row chunk and returns the most semantically similar matches—no SQL needed. Full procedure: 1. Format:.csv only (UTF-8 recommended) 2. Size limits: 50,000 rows and 500 columns per location (select the 20 most relevant columns), upload files up to 50 MB. 3. Header row: First row must contain column names 4. Data types: Automatic schema detection with 80 % confidence threshold 5. Clean data: Remove null values, hidden formulas, merged cells, etc --- ## **Semantic Search Intelligence** GHL Customer Care converts each table row into vector embeddings so the bot can “understand” meanings rather than exact words. This enables queries like “Show me customers who complained about billing” or “Which orders shipped overnight last week?” The engine compares the user’s question to every row chunk and returns the most semantically similar matches—no SQL needed. --- ## **Smart Table Processing** Behind the scenes, GHL Customer Care: - Detects column types (text, number, date, etc.) with 80 % accuracy - Chunks rows into groups of five (max 2,000 characters) for efficient indexing - Stores chunk metadata so answers can reference the correct records --- ## **Frequently Asked Questions** **Q: Can I upload Excel (.xlsx) files?** Not yet—export or save your sheet as CSV before uploading. **Q: How soon are new CSV uploads available to bots?** Typically within a few minutes—the indexing progress bar will show when processing is complete. **Q: Does Table Search support filters or sorting in the query?** Filtering, comparison, and sorting features are coming soon; for now, ask descriptive questions or refine with follow-ups. **Q: Will table data appear in the Response Info sidebar?** Yes—rows that informed the answer are cited, so you can verify or edit them on the spot. **Q: Can I restrict table access to specific bots?** Yes—only bots linked to the Knowledge Base containing your Table Source can query it. **Q: How is privacy handled for sensitive CSV data?** Table Sources inherit existing Knowledge Base security; only users with access to that Knowledge Base can see or query the data. --- ## **Related Articles** - [Conversation AI - New Knowledge Sources & Quality Upgrades](https://docs.ghlcustomercare.com/docs/ai-employee/conversation-ai-training-bots/conversation-ai-new-knowledge-sources-quality-upgrades)  - [Knowledge Base Integration for Voice AI Agents](https://docs.ghlcustomercare.com/docs/ai-employee/voice-ai/knowledge-base-integration-for-voice-ai-agents)  - [View & Edit AI Response Info in Conversations](https://docs.ghlcustomercare.com/docs/conversations/conversations/view-edit-ai-response-info-in-conversations) --- Documentation for GHL Customer Care. Support: support@ghlcustomercare.com