haystack/docs/_src/tutorials/tutorials/3.md

<!---
title: "Tutorial 3"
metaTitle: "Build a QA System Without Elasticsearch"
metaDescription: ""
slug: "/docs/tutorial3"
date: "2020-09-03"
id: "tutorial3md"
--->

# Build a QA System Without Elasticsearch

EXECUTABLE VERSION: [*colab*](https://colab.research.google.com/github/deepset-ai/haystack/blob/master/tutorials/Tutorial3_Basic_QA_Pipeline_without_Elasticsearch.ipynb)

Haystack provides alternatives to Elasticsearch for developing quick prototypes.

You can use an `InMemoryDocumentStore` or a `SQLDocumentStore`(with SQLite) as the document store.

If you are interested in more feature-rich Elasticsearch, then please refer to the Tutorial 1. 


```python
# Install the latest release of Haystack in your own environment 
#! pip install farm-haystack

# Install the latest master of Haystack and install the version of torch that works with the colab GPUs
!pip install git+https://github.com/deepset-ai/haystack.git
!pip install torch==1.6.0+cu101 -f https://download.pytorch.org/whl/torch_stable.html
```


```python
from haystack import Finder
from haystack.preprocessor.cleaning import clean_wiki_text
from haystack.preprocessor.utils import convert_files_to_dicts, fetch_archive_from_http
from haystack.reader.farm import FARMReader
from haystack.reader.transformers import TransformersReader
from haystack.utils import print_answers
```

## Document Store



```python
# In-Memory Document Store
from haystack.document_store.memory import InMemoryDocumentStore
document_store = InMemoryDocumentStore()
```


```python
# SQLite Document Store
# from haystack.document_store.sql import SQLDocumentStore
# document_store = SQLDocumentStore(url="sqlite:///qa.db")
```

## Preprocessing of documents

Haystack provides a customizable pipeline for:
 - converting files into texts
 - cleaning texts
 - splitting texts
 - writing them to a Document Store

In this tutorial, we download Wikipedia articles on Game of Thrones, apply a basic cleaning function, and index them in Elasticsearch.


```python
# Let's first get some documents that we want to query
# Here: 517 Wikipedia articles for Game of Thrones
doc_dir = "data/article_txt_got"
s3_url = "https://s3.eu-central-1.amazonaws.com/deepset.ai-farm-qa/datasets/documents/wiki_gameofthrones_txt.zip"
fetch_archive_from_http(url=s3_url, output_dir=doc_dir)

# convert files to dicts containing documents that can be indexed to our datastore
# You can optionally supply a cleaning function that is applied to each doc (e.g. to remove footers)
# It must take a str as input, and return a str.
dicts = convert_files_to_dicts(dir_path=doc_dir, clean_func=clean_wiki_text, split_paragraphs=True)

# We now have a list of dictionaries that we can write to our document store.
# If your texts come from a different source (e.g. a DB), you can of course skip convert_files_to_dicts() and create the dictionaries yourself.
# The default format here is: {"name": "<some-document-name>, "text": "<the-actual-text>"}

# Let's have a look at the first 3 entries:
print(dicts[:3])
# Now, let's write the docs to our DB.
document_store.write_documents(dicts)
```

## Initalize Retriever, Reader,  & Finder

### Retriever

Retrievers help narrowing down the scope for the Reader to smaller units of text where a given question could be answered. 

With InMemoryDocumentStore or SQLDocumentStore, you can use the TfidfRetriever. For more retrievers, please refer to the tutorial-1.


```python
# An in-memory TfidfRetriever based on Pandas dataframes

from haystack.retriever.sparse import TfidfRetriever
retriever = TfidfRetriever(document_store=document_store)
```

### Reader

A Reader scans the texts returned by retrievers in detail and extracts the k best answers. They are based
on powerful, but slower deep learning models.

Haystack currently supports Readers based on the frameworks FARM and Transformers.
With both you can either load a local model or one from Hugging Face's model hub (https://huggingface.co/models).

**Here:** a medium sized RoBERTa QA model using a Reader based on FARM (https://huggingface.co/deepset/roberta-base-squad2)

**Alternatives (Reader):** TransformersReader (leveraging the `pipeline` of the Transformers package)

**Alternatives (Models):** e.g. "distilbert-base-uncased-distilled-squad" (fast) or "deepset/bert-large-uncased-whole-word-masking-squad2" (good accuracy)

**Hint:** You can adjust the model to return "no answer possible" with the no_ans_boost. Higher values mean the model prefers "no answer possible"

#### FARMReader


```python
# Load a  local model or any of the QA models on
# Hugging Face's model hub (https://huggingface.co/models)

reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=False)
```

#### TransformersReader


```python
# Alternative:
# reader = TransformersReader(model="distilbert-base-uncased-distilled-squad", tokenizer="distilbert-base-uncased", use_gpu=-1)
```

### Finder

The Finder sticks together reader and retriever in a pipeline to answer our actual questions. 


```python
finder = Finder(reader, retriever)
```

## Voilà! Ask a question!


```python
# You can configure how many candidates the reader and retriever shall return
# The higher top_k_retriever, the better (but also the slower) your answers. 
prediction = finder.get_answers(question="Who is the father of Arya Stark?", top_k_retriever=10, top_k_reader=5)
```


```python
# prediction = finder.get_answers(question="Who created the Dothraki vocabulary?", top_k_reader=5)
# prediction = finder.get_answers(question="Who is the sister of Sansa?", top_k_reader=5)
```


```python
print_answers(prediction, details="minimal")
```