Update Prompt

.cache/models--sentence-transformers--paraphrase-MiniLM-L3-v2/refs/main

@@ -0,0 +1 @@
+4ca70771034acceecb2e72475f72050fcdde4ddc

.cache/models--sentence-transformers--paraphrase-MiniLM-L3-v2/snapshots/4ca70771034acceecb2e72475f72050fcdde4ddc/1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

.cache/models--sentence-transformers--paraphrase-MiniLM-L3-v2/snapshots/4ca70771034acceecb2e72475f72050fcdde4ddc/README.md

@@ -0,0 +1,114 @@
+---
+license: apache-2.0
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+datasets:
+- flax-sentence-embeddings/stackexchange_xml
+- s2orc
+- ms_marco
+- wiki_atomic_edits
+- snli
+- multi_nli
+- embedding-data/altlex
+- embedding-data/simple-wiki
+- embedding-data/flickr30k-captions
+- embedding-data/coco_captions
+- embedding-data/sentence-compression
+- embedding-data/QQP
+- yahoo_answers_topics
+pipeline_tag: sentence-similarity
+---
+
+# sentence-transformers/paraphrase-MiniLM-L3-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('sentence-transformers/paraphrase-MiniLM-L3-v2')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-MiniLM-L3-v2')
+model = AutoModel.from_pretrained('sentence-transformers/paraphrase-MiniLM-L3-v2')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, max pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+
+This model was trained by [sentence-transformers](https://www.sbert.net/). 
+        
+If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
+```bibtex 
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "http://arxiv.org/abs/1908.10084",
+}
+```

.cache/models--sentence-transformers--paraphrase-MiniLM-L3-v2/snapshots/4ca70771034acceecb2e72475f72050fcdde4ddc/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "old_models/paraphrase-MiniLM-L3-v2/0_Transformer",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.7.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

.cache/models--sentence-transformers--paraphrase-MiniLM-L3-v2/snapshots/4ca70771034acceecb2e72475f72050fcdde4ddc/config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  }
+}

.cache/models--sentence-transformers--paraphrase-MiniLM-L3-v2/snapshots/4ca70771034acceecb2e72475f72050fcdde4ddc/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1e4e2d420c664973037c3c73125d7a8fc69952495093ef8f50596f8943a433
+size 69569488

.cache/models--sentence-transformers--paraphrase-MiniLM-L3-v2/snapshots/4ca70771034acceecb2e72475f72050fcdde4ddc/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

.cache/models--sentence-transformers--paraphrase-MiniLM-L3-v2/snapshots/4ca70771034acceecb2e72475f72050fcdde4ddc/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

.cache/models--sentence-transformers--paraphrase-MiniLM-L3-v2/snapshots/4ca70771034acceecb2e72475f72050fcdde4ddc/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

.cache/models--sentence-transformers--paraphrase-MiniLM-L3-v2/snapshots/4ca70771034acceecb2e72475f72050fcdde4ddc/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "name_or_path": "nreimers/MiniLM-L3-H384-uncased", "do_basic_tokenize": true, "never_split": null, "model_max_length": 512}

app.py

@@ -23,7 +23,7 @@ logging.getLogger('tensorflow').setLevel(logging.ERROR)
 from fastapi import FastAPI, Request, HTTPException, Depends, Header
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
-from parser import parse_pdf_from_url, parse_pdf_from_file
+from pdf_parser import parse_pdf_from_url_multithreaded as parse_pdf_from_url, parse_pdf_from_file_multithreaded as parse_pdf_from_file
 from embedder import build_faiss_index, preload_model
 from retriever import retrieve_chunks
 from llm import query_gemini

main.py

@@ -17,7 +17,7 @@ logging.getLogger('tensorflow').setLevel(logging.ERROR)
 from fastapi import FastAPI, Request, HTTPException, Depends, Header
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
-from parser import parse_pdf_from_url, parse_pdf_from_file
+from pdf_parser import parse_pdf_from_url, parse_pdf_from_file
 from embedder import build_faiss_index, preload_model
 from retriever import retrieve_chunks
 from llm import query_gemini

parser.py

@@ -1,29 +0,0 @@
-import fitz  # PyMuPDF
-import requests
-from io import BytesIO
-import time
-
-def parse_pdf_from_url(url):
-    res = requests.get(url)
-    doc = fitz.open(stream=BytesIO(res.content), filetype="pdf")
-    chunks = []
-    for page in doc:
-        text = page.get_text()
-        if text.strip():
-            chunks.append(text)
-    doc.close()
-    return chunks
-
-def parse_pdf_from_file(file_path):
-    """Parse a local PDF file and extract text chunks"""
-    try:
-        doc = fitz.open(file_path)
-        chunks = []
-        for page in doc:
-            text = page.get_text()
-            if text.strip():
-                chunks.append(text)
-        doc.close()
-        return chunks
-    except Exception as e:
-        raise Exception(f"Error parsing PDF file {file_path}: {str(e)}")

pdf_parser.py

@@ -0,0 +1,43 @@
+import fitz  # PyMuPDF
+import requests
+from io import BytesIO
+from concurrent.futures import ThreadPoolExecutor
+import os
+
+def extract_page_text(page):
+    text = page.get_text()
+    return text if text.strip() else None
+
+def parse_pdf_from_url_multithreaded(url, max_workers=None):
+    # Automatically detect and use all available CPU cores if max_workers not set
+    if max_workers is None:
+        max_workers = os.cpu_count() or 8
+
+    res = requests.get(url)
+    doc = fitz.open(stream=BytesIO(res.content), filetype="pdf")
+    pages = [page for page in doc]
+    chunks = [None] * len(pages)
+    
+    # Process pages in parallel, preserving page order
+    with ThreadPoolExecutor(max_workers=max_workers) as executor:
+        results = list(executor.map(extract_page_text, pages))
+    
+    # Keep only non-empty page results, preserving order
+    doc.close()
+    return [r for r in results if r]
+
+def parse_pdf_from_file_multithreaded(file_path, max_workers=None):
+    if max_workers is None:
+        max_workers = os.cpu_count() or 8
+
+    try:
+        doc = fitz.open(file_path)
+        pages = [page for page in doc]
+        chunks = [None] * len(pages)
+        
+        with ThreadPoolExecutor(max_workers=max_workers) as executor:
+            results = list(executor.map(extract_page_text, pages))
+        doc.close()
+        return [r for r in results if r]
+    except Exception as e:
+        raise Exception(f"Error parsing PDF file {file_path}: {str(e)}")