Enhancing LLM Accuracy Using MongoDB Vector Search and Unstructured.io Metadata

1
# Install Unstructured partition for PDF and dependencies
2
pip install unstructured[“pdf”]
3
!apt-get -qq install poppler-utils tesseract-ocr
4
!pip install -q --user --upgrade pillow
5
6
pip install pymongo
7
pip install sentence-transformers

1
from unstructured.partition.pdf import partition_pdf
2
3
elements = partition_pdf("example-docs/Attention is All You Need.pdf",
4
                         strategy="hi_res",
5
                         infer_table_structured=True)

1
display(*[(type(element), element.text) for element in elements[14:18]]) 

1
(unstructured.documents.elements.NarrativeText,
2
 'The dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English- to-German translation task, improving over the existing best results, including ensembles, by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.')
3
(unstructured.documents.elements.NarrativeText,
4
 '∗Equal contribution. Listing order is random....

1
from collections import Counter
2
display(Counter(type(element) for element in elements))
3
4
# outputs
5
Counter({unstructured.documents.elements.NarrativeText: 86,
6
         unstructured.documents.elements.Title: 56,
7
         unstructured.documents.elements.Text: 45,
8
         unstructured.documents.elements.Header: 3,
9
         unstructured.documents.elements.Footer: 9,
10
         unstructured.documents.elements.Image: 5,
11
         unstructured.documents.elements.FigureCaption: 5,
12
         unstructured.documents.elements.Formula: 5,
13
         unstructured.documents.elements.ListItem: 43,
14
         unstructured.documents.elements.Table: 4})

1
from unstructured.staging.base import convert_to_dict
2
3
# built-in function to convert elements into Python dictionary
4
records = convert_to_dict(elements)
5
6
# display the first record
7
records[0]
8
9
# output
10
{'type': 'NarrativeText',
11
 'element_id': '6b82d499d67190c0ceffe3a99958e296',
12
 'metadata': {'coordinates': {'points': ((327.6542053222656,
13
     199.8135528564453),
14
    (327.6542053222656, 315.7165832519531),
15
    (1376.0062255859375, 315.7165832519531),
16
    (1376.0062255859375, 199.8135528564453)),
17
   'system': 'PixelSpace',
18
   'layout_width': 1700,
19
   'layout_height': 2200},
20
  'filename': 'Attention is All You Need.pdf',
21
  'last_modified': '2023-10-09T20:15:36',
22
  'filetype': 'application/pdf',
23
  'page_number': 1,
24
  'detection_class_prob': 0.5751863718032837},
25
 'text': 'Provided proper attribution is provided, Google hereby grants permission to reproduce the tables and figures in this paper solely for use in journalistic or scholarly works.'}

1
from sentence_transformers import SentenceTransformer
2
from pprint import pprint
3
4
model = SentenceTransformer('microsoft/mpnet-base')
5
6
# Let's test and check the number of embedding size using this model
7
emb = model.encode("this is a test").tolist()
8
print(len(emb))
9
print(emb[:10])
10
print("\n")
11
12
# output
13
768
14
[-0.15820945799350739, 0.008249259553849697, -0.033347081393003464, …]

1
{
2
  "type": "vectorSearch,
3
  "fields": [{
4
    "path": "embedding",
5
    "dimensions": 768, # the dimension of `mpnet-base` model    
6
    "similarity": "euclidean",
7
    "type": "vector"
8
  }]
9
}

1
for record in records:
2
    txt = record['text']
3
    
4
    # use the embedding model to vectorize the text into the record
5
    record['embedding'] = model.encode(txt).tolist() 
6
7
# print the first record with embedding
8
records[0]
9
10
# output
11
{'type': 'NarrativeText',
12
 'element_id': '6b82d499d67190c0ceffe3a99958e296',
13
 'metadata': {'coordinates': {'points': ((327.6542053222656,
14
     199.8135528564453),
15
    (327.6542053222656, 315.7165832519531),
16
    (1376.0062255859375, 315.7165832519531),
17
    (1376.0062255859375, 199.8135528564453)),
18
   'system': 'PixelSpace',
19
   'layout_width': 1700,
20
   'layout_height': 2200},
21
  'filename': 'Attention is All You Need.pdf',
22
  'last_modified': '2023-10-09T20:15:36',
23
  'filetype': 'application/pdf',
24
  'page_number': 1,
25
  'detection_class_prob': 0.5751863718032837},
26
 'text': 'Provided proper attribution is provided, Google hereby grants permission to reproduce the tables and figures in this paper solely for use in journalistic or scholarly works.',
27
 'embedding': [-0.018366225063800812,
28
  -0.10861606895923615,
29
  0.00344603369012475,
30
  0.04939081519842148,
31
  -0.012352174147963524,
32
  -0.04383034259080887,...],
33
'_id': ObjectId('6524626a6d1d8783bb807943')}
34
}

1
from pymongo.mongo_client import MongoClient
2
from pymongo.server_api import ServerApi
3
4
uri = "<<REPLACE THE URI TO CONNECT TO CLUSTER>>"
5
6
# Create a new client and connect to the server
7
client = MongoClient(uri, server_api=ServerApi('1'))
8
9
# Send a ping to confirm a successful connection
10
try:
11
    client.admin.command('ping')
12
    print("Pinged your deployment. You successfully connected to MongoDB!")
13
except Exception as e:
14
    print(e)

1
db_name = "unstructured_db"
2
collection_name = "unstructured_col"
3
4
# delete all first
5
client[db_name][collection_name].delete_many({})
6
7
# insert
8
client[db_name][collection_name].insert_many(records)

1
query = "Does the encoder contain self-attention layers?"
2
vector_query = model.encode(query).tolist()
3
4
pipeline = [
5
{
6
"$vectorSearch": {
7
        "index":"default",
8
        "queryVector": vector_query,
9
        "path": "embedding",
10
        "limit": 5,
11
        "numCandidates": 50
12
    }
13
  },
14
  {
15
    "$project": {
16
        "embedding": 0,
17
        "_id": 0,
18
        "score": {
19
            "$meta": "searchScore"
20
        },
21
    }
22
  }
23
]
24
25
results = list(client[db_name][collection_name].aggregate(pipeline))

1
{'element_id': '7128012294b85295c89efee3bc5e72d2',
2
  'metadata': {'coordinates': {'layout_height': 2200,
3
                               'layout_width': 1700,
4
                               'points': [[290.50477600097656,
5
                                           1642.1170677777777],
6
                                          [290.50477600097656,
7
                                           1854.9523748867755],
8
                                          [1403.820083618164,
9
                                           1854.9523748867755],
10
                                          [1403.820083618164,
11
                                           1642.1170677777777]],
12
                               'system': 'PixelSpace'},
13
               'detection_class_prob': 0.9979791045188904,
14
               'file_directory': 'example-docs',
15
               'filename': 'Attention is All You Need.pdf',
16
               'filetype': 'application/pdf',
17
               'last_modified': '2023-09-20T17:08:35',
18
               'page_number': 3,
19
               'parent_id': 'd1375b5e585821dff2d1907168985bfe'},
20
  'score': 0.2526094913482666,
21
  'text': 'Decoder: The decoder is also composed of a stack of N = 6 identical '
22
          'layers. In addition to the two sub-layers in each encoder layer, '
23
          'the decoder inserts a third sub-layer, which performs multi-head '
24
          'attention over the output of the encoder stack. Similar to the '
25
          'encoder, we employ residual connections around each of the '
26
          'sub-layers, followed by layer normalization. We also modify the '
27
          'self-attention sub-layer in the decoder stack to prevent positions '
28
          'from attending to subsequent positions. This masking, combined with '
29
          'fact that the output embeddings are offset by one position, ensures '
30
          'that the predictions for position i can depend only on the known '
31
          'outputs at positions less than i.',
32
  'type': 'NarrativeText'}

1
import os
2
import openai
3
4
# Get the API key from the env
5
openai.api_key = os.getenv("OPENAI_API_KEY")

1
response = openai.ChatCompletion.create(
2
  model="gpt-4",
3
  messages=[
4
        {"role": "system", "content": "You are a useful assistant. Use the assistant's content to answer the user's query \
5
        Summarize your answer using the 'texts' and cite the 'page_number' and 'filename' metadata in your reply."},
6
        {"role": "assistant", "content": context},
7
        {"role": "user", "content": query},
8
    ],
9
    temperature = 0.2
10
)

1
User query: "Does the encoder contain self-attention layers?"

1
response = openai.ChatCompletion.create(
2
  model="gpt-4",
3
  messages=[
4
        {"role": "system", "content": "You are a useful assistant. Use the assistant's content to answer the user's query \
5
        Summarize your answer using the 'texts' and cite the 'page_number' and 'filename' metadata in your reply."},
6
        {"role": "assistant", "content": context},
7
        {"role": "user", "content": query},
8
    ],
9
    temperature = 0.2
10
)
11
12
print(response)
13
14
# output
15
{
16
  "id": "chatcmpl-87rNcLaEYREimtuWa0bpymWiQbZze",
17
  "object": "chat.completion",
18
  "created": 1696884180,
19
  "model": "gpt-4-0613",
20
  "choices": [
21
    {
22
      "index": 0,
23
      "message": {
24
        "role": "assistant",
25
        "content": "Yes, the encoder does contain self-attention layers. This is evident from the text on page 5 of the document \"Attention is All You Need.pdf\"."
26
      },
27
      "finish_reason": "stop"
28
    }
29
  ],
30
  "usage": {
31
    "prompt_tokens": 1628,
32
    "completion_tokens": 32,
33
    "total_tokens": 1660
34
  }
35
}