initialize embeddings

App/Embedding/EmbeddingRoutes.py

@@ -15,9 +15,18 @@ async def create_embeddings(task_id):
 
     return
 
+@embeddigs_router.get("/create_summary")
+async def create_embeddings(task_id):
+    item = await Transcriptions.objects.filter(task_id=task_id).first()
+    temp = item.content
+    chunks = generateChunks(temp, task_id)
+    encode(chunks)
+
+    return
+
 
 # search
 # update?
-@embeddigs_router.get("/search_embeddings")
-async def search_embeddings(query, task_id):
+@embeddigs_router.post("/search_embeddings")
+async def search_embeddings(query:str, task_id:str):
     return search(query=query, task_id=task_id)

App/Embedding/utils/Initialize.py

@@ -1,14 +1,13 @@
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.docstore.document import Document
 from langchain.vectorstores import MongoDBAtlasVectorSearch
-from langchain.vectorstores import FAISS
 from pymongo import MongoClient
 from motor.motor_asyncio import AsyncIOMotorClient
-import os
+import os,pprint
 
 
-completion_base=os.environ.get("completion_base")
-openai_api_key=os.environ.get("openai_api_key")
+completion_base = os.environ.get("completion_base")
+openai_api_key = os.environ.get("openai_api_key")
 mongoDB = os.environ.get("MONGO_DB")
 template = """### Given the following context 
 ### Context
@@ -54,9 +53,7 @@ async def fetch_data(question, context):
 
 
 async def delete_documents(task_id):
-    client = AsyncIOMotorClient(
-       mongoDB
-    )
+    client = AsyncIOMotorClient(mongoDB)
     db = client["transcriptions"]
     collection = db["videos"]
 
@@ -95,9 +92,7 @@ def generateChunks(chunks, task_id, n=100):
 
 
 def search(query: str, task_id: str):
-    mongo_client = MongoClient(
-       mongoDB
-    )
+    mongo_client = MongoClient(mongoDB)
     model_name = "BAAI/bge-base-en"
     collection = mongo_client["transcriptions"]["videos"]
     embeddings = HuggingFaceEmbeddings(model_name=model_name)
@@ -120,7 +115,8 @@ def search(query: str, task_id: str):
     )
     # data =[d.dict() for d in data]
     # print(data[0].metadata.exclude({'_id','embedding'}))
-    return [{"text": d.page_content} for d in data]
+    pprint.pprint(data[0].metadata)
+    return [{"text": d.page_content,'start':d.metadata['start'],"end":d.metadata['end']} for d in data]
     # agent =vectorstore.as_retriever(
 
     # )
@@ -128,9 +124,7 @@ def search(query: str, task_id: str):
 
 
 def encode(temp: list[Document]):
-    mongo_client = MongoClient(
-       mongoDB
-    )
+    mongo_client = MongoClient(mongoDB)
     model_name = "BAAI/bge-base-en"
     collection = mongo_client["transcriptions"]["videos"]
     embeddings = HuggingFaceEmbeddings(model_name=model_name)