Update app.py

app.py

@@ -8,7 +8,7 @@ import langchain
 import time
 from cnocr import CnOcr
 import pinecone
-
+import openai
 from langchain.vectorstores import Pinecone
 from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.text_splitter import CharacterTextSplitter
@@ -39,45 +39,7 @@ all_max_len = 3000
 
 # Initialize Pinecone client and create an index
 pinecone.init(api_key="ffb1f594-0915-4ebf-835f-c1eaa62fdcdc",environment = "us-west4-gcp-free")
-index = pinecone.Index(index_name="test")
-
-
-def pine(data):
-    char_text_spliter = CharacterTextSplitter(chunk_size = 1000, chunk_overlap=0)
-    # doc_text = char_text_spliter.split_documents(data)
-    doc_spilt = []
-    data = data.split(" ")
-    # print(len(data))
-    
-    c = 0
-    check = 0
-    for i in data:
-      # print(i)
-      if c == 350:
-        text = " ".join(data[check: check + c])
-        print(text)
-        print(check)
-        doc_spilt.append(text)
-        check = check + c
-        c = 0
-      else:
-        c = c+1
-
-
-    Embedding_model = "text-embedding-ada-002"
-    embeddings = OpenAIEmbeddings(openai_api_key="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")
-
-    pinecone.init(api_key = "ffb1f594-0915-4ebf-835f-c1eaa62fdcdc",
-              environment = "us-west4-gcp-free"
-              )
-
-    index_name = "test"
-    docstore = Pinecone.from_texts([d for d in doc_spilt],embeddings,index_name = index_name,namespace='a1')
-
-    return ''
-
-
-    
+index = pinecone.Index(index_name="test")    
 
 
 def get_emb(text):
@@ -193,7 +155,7 @@ def up_file(fls):
 
     #Pdf Extracting
     for idx, file in enumerate(pdf):
-        print("11111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111111")
+        print("11111")
         #print(file.name)
         with pdfplumber.open(file) as pdf:
             for i in range(len(pdf.pages)):
@@ -270,6 +232,39 @@ def up_file(fls):
         value="Processing")
 
 
+def pine(data):
+    char_text_spliter = CharacterTextSplitter(chunk_size = 1000, chunk_overlap=0)
+    # doc_text = char_text_spliter.split_documents(data)
+    doc_spilt = []
+    data = data.split(" ")
+    # print(len(data))
+    
+    c = 0
+    check = 0
+    for i in data:
+      # print(i)
+      if c == 350:
+        text = " ".join(data[check: check + c])
+        print(text)
+        print(check)
+        doc_spilt.append(text)
+        check = check + c
+        c = 0
+      else:
+        c = c+1
+
+
+    Embedding_model = "text-embedding-ada-002"
+    embeddings = OpenAIEmbeddings(openai_api_key="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")
+
+    pinecone.init(api_key = "ffb1f594-0915-4ebf-835f-c1eaa62fdcdc",
+              environment = "us-west4-gcp-free"
+              )
+
+    index_name = "test"
+    docstore = Pinecone.from_texts([d for d in doc_spilt],embeddings,index_name = index_name,namespace='a1')
+
+    return ''