Add pandas example by ofermend · Pull Request #36 · vectara/example-notebooks

ofermend · 2026-03-11T05:10:20Z

No description provided.

added reranker instructions example (notebook 8) updated messaging

Copilot

Pull request overview

This PR expands the Vectara API tutorial notebook series by adding new end-to-end examples (data analysis Lambda tools with NumPy/Pandas, and reranker instructions with Qwen3), while also refreshing the “About Vectara” boilerplate and updating tutorial documentation.

Changes:

Update notebooks/api-examples/README.md to reflect additional notebooks and endpoints.
Add Notebook 7 (NumPy/Pandas Lambda tools for data analysis) and Notebook 8 (Qwen3 reranker instructions).
Refresh “About Vectara” text formatting/content across Notebooks 1–4 and add CLAUDE.md repo guidance.

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 6 comments.

Show a summary per file

File	Description
notebooks/api-examples/README.md	Updates tutorial narrative, adds Notebook 6/7 sections, tutorial flow, and endpoint mapping.
notebooks/api-examples/7-lambda-tools-data-analysis.ipynb	New notebook demonstrating creation/use of Python Lambda tools leveraging NumPy/Pandas.
notebooks/api-examples/8-reranker-instructions.ipynb	New notebook demonstrating reranker instructions with `qwen3-reranker`.
notebooks/api-examples/1-corpus-creation.ipynb	Updates “About Vectara” section text/formatting.
notebooks/api-examples/2-data-ingestion.ipynb	Updates “About Vectara” section text/formatting.
notebooks/api-examples/3-query-api.ipynb	Updates “About Vectara” section text/formatting.
notebooks/api-examples/4-agent-api.ipynb	Updates “About Vectara” section text/formatting.
CLAUDE.md	Adds repository usage guidance for Claude Code.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-03-11T05:15:34Z

notebooks/api-examples/7-lambda-tools-data-analysis.ipynb

+   "id": "cell-15",
+   "metadata": {},
+   "source": [
+    "## Step 5: Create a Session and Test the Agent\n",


Step numbering skips from Step 3 to "Step 5" here, which is confusing when following the tutorial. Renumber this to Step 4 (or add the missing Step 4 section if something was omitted).

Suggested change

"## Step 5: Create a Session and Test the Agent\n",

"## Step 4: Create a Session and Test the Agent\n",

Copilot · 2026-03-11T05:15:34Z

notebooks/api-examples/8-reranker-instructions.ipynb

+    "    print(\"\\n=== Top Search Results ===\")\n",
+    "    for i, sr in enumerate(result.get('search_results', [])[:5], 1):\n",
+    "        meta = sr.get('document_metadata', {})\n",
+    "        print(f\"\\n--- Result {i} (score: {sr.get('score', 'N/A'):.4f}) ---\")\n",


This format expression will raise a TypeError if score is missing or non-numeric (because the default is the string 'N/A'). Use a numeric default (e.g., 0.0) or branch formatting based on whether score is present.

Suggested change

" print(f\"\\n--- Result {i} (score: {sr.get('score', 'N/A'):.4f}) ---\")\n",

" score = sr.get('score')\n",

" if isinstance(score, (int, float)):\n",

" score_str = f\"{score:.4f}\"\n",

" else:\n",

" score_str = \"N/A\"\n",

" print(f\"\\n--- Result {i} (score: {score_str}) ---\")\n",

Copilot · 2026-03-11T05:15:35Z

notebooks/api-examples/README.md

 # Vectara API Tutorial Series

-This tutorial series provides a comprehensive, hands-on introduction to building RAG (Retrieval-Augmented Generation) applications using Vectara's REST API. Through five progressive notebooks, you'll learn to create corpora, ingest data, query information, build intelligent AI agents, and orchestrate multi-agent workflows.
+This tutorial series provides a comprehensive, hands-on introduction to building RAG (Retrieval-Augmented Generation) applications using Vectara's REST API. Through seven progressive notebooks, you'll learn to create corpora, ingest data, query information, build intelligent AI agents, orchestrate multi-agent workflows, work with file artifacts, and create data analysis tools with NumPy and Pandas.


The README says there are "seven progressive notebooks", but this directory now contains 8 notebooks (including 8-reranker-instructions.ipynb). Update the count and ensure the tutorial overview/flow includes Notebook 8 (or explicitly label it as an optional/bonus notebook).

Suggested change

This tutorial series provides a comprehensive, hands-on introduction to building RAG (Retrieval-Augmented Generation) applications using Vectara's REST API. Through seven progressive notebooks, you'll learn to create corpora, ingest data, query information, build intelligent AI agents, orchestrate multi-agent workflows, work with file artifacts, and create data analysis tools with NumPy and Pandas.

This tutorial series provides a comprehensive, hands-on introduction to building RAG (Retrieval-Augmented Generation) applications using Vectara's REST API. Through eight progressive notebooks, you'll learn to create corpora, ingest data, query information, build intelligent AI agents, orchestrate multi-agent workflows, work with file artifacts, and create data analysis tools with NumPy and Pandas.

Copilot · 2026-03-11T05:15:35Z

notebooks/api-examples/README.md

+- Build tools for statistical analysis, trend detection, and data transformation
+- Combine multiple data analysis tools in agent workflows
+
+**What you'll build:**
+Three **Data Analysis Lambda Tools**:
+1. **Statistical Analyzer**: Descriptive statistics, correlations, percentiles using Pandas
+2. **Trend Analyzer**: Moving averages, growth rates, linear regression using NumPy
+3. **Data Transformer**: Normalization, missing value handling, outlier removal, aggregation


This section claims Notebook 7 builds three Lambda tools (including a "Data Transformer"), but 7-lambda-tools-data-analysis.ipynb only defines statistical_analyzer and trend_analyzer (no transformer tool found). Either add the missing tool to the notebook or adjust this README to match what the notebook actually builds.

Suggested change

- Build tools for statistical analysis, trend detection, and data transformation

- Combine multiple data analysis tools in agent workflows

**What you'll build:**

Three **Data Analysis Lambda Tools**:

1. **Statistical Analyzer**: Descriptive statistics, correlations, percentiles using Pandas

2. **Trend Analyzer**: Moving averages, growth rates, linear regression using NumPy

3. **Data Transformer**: Normalization, missing value handling, outlier removal, aggregation

- Build tools for statistical analysis and trend detection

- Combine multiple data analysis tools in agent workflows

**What you'll build:**

Two **Data Analysis Lambda Tools**:

1. **Statistical Analyzer**: Descriptive statistics, correlations, percentiles using Pandas

2. **Trend Analyzer**: Moving averages, growth rates, linear regression using NumPy

Copilot · 2026-03-11T05:15:35Z

notebooks/api-examples/README.md

+    "code": """
+import pandas as pd
+import numpy as np
+
+def process(data: str, columns: str = "", operations: str = "describe") -> dict:
+    df = pd.DataFrame(json.loads(data))
+    # ... compute statistics


The code snippet uses json.loads(data) but doesn't import json, so it won't run as written. Add an import json in the snippet (or adjust the example to avoid json.loads).

Copilot · 2026-03-11T05:15:35Z

notebooks/api-examples/README.md

+| `POST /v2/agents` | Create agent | 4, 5, 6, 7 |
+| `POST /v2/agents/{key}/sessions` | Create session | 4, 5, 6, 7 |
+| `POST /v2/agents/{key}/sessions/{key}/events` | Send messages / Upload artifacts | 4, 5, 6, 7 |
 | `GET /v2/agents/{key}/sessions/{key}/events` | Get conversation history | 4 |
+| `GET /v2/agents/{key}/sessions/{key}/artifacts` | List session artifacts | 6 |


The endpoint mapping table hasn’t been updated for the new Notebook 8 (which uses POST /v2/query). Update the table so the "Notebook" column references 8 where applicable (at minimum for /v2/query).

Copilot

Pull request overview

Copilot reviewed 9 out of 9 changed files in this pull request and generated 1 comment.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-03-11T13:20:48Z

notebooks/api-examples/7-lambda-tools-data-analysis.ipynb

+    "            return {\"success\": False, \"error\": f\"None of the specified columns found. Available: {list(df.columns)}\"}\n",
+    "        df_analysis = df[valid_cols]\n",
+    "    else:\n",
+    "        df_analysis = df.select_dtypes(include=[np.number])\n",


When columns is empty, df_analysis = df.select_dtypes(include=[np.number]) can produce an empty DataFrame (e.g., if the input data has no numeric columns). Downstream operations like describe() will then raise (pandas cannot describe a DataFrame without columns). Add an explicit guard after selecting numeric columns to return a clear error (or fall back to describe(include='all')) when there are no columns to analyze.

Suggested change

" df_analysis = df.select_dtypes(include=[np.number])\n",

" df_analysis = df.select_dtypes(include=[np.number])\n",

" if df_analysis.shape[1] == 0:\n",

" return {\"success\": False, \"error\": \"No numeric columns found to analyze.\"}\n",

ofermend added 4 commits February 3, 2026 07:06

added example with pandas

e731c97

updated lambda tools example

195b91e

updated

7fd4497

fixed notebook 7

31f85b4

added reranker instructions example (notebook 8) updated messaging

ofermend requested a review from Copilot March 11, 2026 05:10

Copilot started reviewing on behalf of ofermend March 11, 2026 05:10 View session

Copilot AI reviewed Mar 11, 2026

View reviewed changes

ofermend added 2 commits March 10, 2026 22:53

minor updates

4e17883

updated README

c6e2420

ofermend requested a review from Copilot March 11, 2026 13:14

Copilot started reviewing on behalf of ofermend March 11, 2026 13:15 View session

Copilot AI reviewed Mar 11, 2026

View reviewed changes

ofermend merged commit a593d59 into main Mar 11, 2026
4 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add pandas example#36

Add pandas example#36
ofermend merged 6 commits intomainfrom
add_pandas_example

ofermend commented Mar 11, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Mar 11, 2026

Uh oh!

Copilot AI Mar 11, 2026

Uh oh!

Copilot AI Mar 11, 2026

Uh oh!

Copilot AI Mar 11, 2026

Uh oh!

Copilot AI Mar 11, 2026

Uh oh!

Copilot AI Mar 11, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Mar 11, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

	"## Step 5: Create a Session and Test the Agent\n",
	"## Step 4: Create a Session and Test the Agent\n",

-    "        print(f\"\\n--- Result {i} (score: {sr.get('score', 'N/A'):.4f}) ---\")\n",
+    "        score = sr.get('score')\n",
+    "        if isinstance(score, (int, float)):\n",
+    "            score_str = f\"{score:.4f}\"\n",
+    "        else:\n",
+    "            score_str = \"N/A\"\n",
+    "        print(f\"\\n--- Result {i} (score: {score_str}) ---\")\n",

Conversation

ofermend commented Mar 11, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Mar 11, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 11, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 11, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 11, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 11, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 11, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Mar 11, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants