Back to Prompt Library
planning

LlamaIndex Data Ingestion & Indexing Strategy

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Agent for Enterprise M&A Due Diligence

Format
Code-aware
Lines
14
Sections
5
Linked challenge
Agent for Enterprise M&A Due Diligence

Prompt source

Original prompt text with formatting preserved for inspection.

14 lines
5 sections
No variables
1 code block
Outline a LlamaIndex data ingestion and indexing strategy for M&A due diligence. Describe how you would handle various data types (PDF financial reports, web articles from Skyvern, internal company databases). Specify the types of indexes you would use (e.g., VectorStoreIndex, KeywordTableIndex) and why. Provide a Python snippet demonstrating basic document loading and index creation using LlamaIndex `SimpleDirectoryReader` and `VectorStoreIndex`.

```python
from llama_index.readers.simple_directory import SimpleDirectoryReader
from llama_index.core import VectorStoreIndex, Settings
from llama_index.llms.gemini import Gemini
from llama_index.embeddings.ollama import OllamaEmbedding

# Configure settings for Gemini LLM and Ollama embeddings
Settings.llm = Gemini(model="gemini-pro", temperature=0.0)
Settings.embed_model = OllamaEmbedding(model_name="nomic-embed-text")

# Simulate loading documents
documents = SimpleDirectoryReader(input_files=["path/to/financial_report.pdf", "path/to/market_analysis.txt"]).load_data()

# Create a vector index
index = VectorStoreIndex.from_documents(documents)
```

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.

Tune next

Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.

Verify after

Check whether the prompt asks for the right evidence, confidence signal, and escalation path.