Fix/file upload explore (#412)

Author: gozineb

backend/models/brains.py

@@ -40,7 +40,6 @@ def brain_size(self):
     def remaining_brain_size(self):
         return float(self.max_brain_size) - self.brain_size
 
-
     @classmethod
     def create(cls, *args, **kwargs):
         commons = common_dependencies()
@@ -79,18 +78,17 @@ def create_brain(self):
         self.id = response.data[0]['brain_id']   
         return response.data
 
-    def create_brain_user(self, user_id : UUID, rights, default_brain):
+    def create_brain_user(self, user_id: UUID, rights, default_brain):
         commons = common_dependencies()
-        response = commons["supabase"].table("brains_users").insert({"brain_id": str(self.id), "user_id":str( user_id), "rights": rights, "default_brain": default_brain}).execute()
+        response = commons["supabase"].table("brains_users").insert({"brain_id": str(self.id), "user_id": str(user_id), "rights": rights, "default_brain": default_brain}).execute()
 
-
         return response.data
 
-    def create_brain_vector(self, vector_id):
+    def create_brain_vector(self, vector_id, file_sha1):
         response = (
             self.commons["supabase"]
             .table("brains_vectors")
-            .insert({"brain_id": str(self.id), "vector_id": str(vector_id)})
+            .insert({"brain_id": str(self.id), "vector_id": str(vector_id), "file_sha1": file_sha1})
             .execute()
         )
         return response.data
@@ -115,7 +113,7 @@ def update_brain_with_file(self, file_sha1: str):
         # not  used
         vector_ids = self.get_vector_ids_from_file_sha1(file_sha1)
         for vector_id in vector_ids:
-            self.create_brain_vector(vector_id)
+            self.create_brain_vector(vector_id, file_sha1)
 
     def get_unique_brain_files(self):
         """
@@ -142,15 +140,24 @@ def get_unique_brain_files(self):
 
         return self.files
 
-    def get_unique_files_from_vector_ids(self, vectors_ids : List[int]):
+    def get_unique_files_from_vector_ids(self, vectors_ids: List[int]):
         # Move into Vectors class
         """
         Retrieve unique user data vectors.
         """
-        vectors_response = self.commons['supabase'].table("vectors").select(
-            "name:metadata->>file_name, size:metadata->>file_size", count="exact") \
+        print('vectors_ids', vectors_ids)
+        print('tuple(vectors_ids)', tuple(vectors_ids))
+        if len(vectors_ids) == 1:
+            vectors_response = self.commons['supabase'].table("vectors").select(
+                "name:metadata->>file_name, size:metadata->>file_size", count="exact") \
+                .filter("id", "eq", vectors_ids[0])\
+                .execute()
+        else:
+            vectors_response = self.commons['supabase'].table("vectors").select(
+                "name:metadata->>file_name, size:metadata->>file_size", count="exact") \
                 .filter("id", "in", tuple(vectors_ids))\
                 .execute()
+            
         documents = vectors_response.data  # Access the data from the response
         # Convert each dictionary to a tuple of items, then to a set to remove duplicates, and then back to a dictionary
         unique_files = [dict(t) for t in set(tuple(d.items()) for d in documents)]
@@ -187,6 +194,7 @@ def get_default_user_brain(user: User):
         .execute()
     )
 
+    print("Default brain response:", response.data)
     default_brain_id = response.data[0]["brain_id"] if response.data else None
 
     print(f"Default brain id: {default_brain_id}")

backend/models/files.py

@@ -6,24 +6,26 @@
 from fastapi import UploadFile
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from logger import get_logger
+from models.brains import Brain
 from models.settings import CommonsDep, common_dependencies
 from pydantic import BaseModel
 from utils.file import compute_sha1_from_file
 
 logger = get_logger(__name__)
 
+
 class File(BaseModel):
     id: Optional[UUID] = None
     file: Optional[UploadFile]
     file_name: Optional[str] = ""
     file_size: Optional[int] = ""
     file_sha1: Optional[str] = ""
-    vectors_ids: Optional[int]=[]
+    vectors_ids: Optional[int] = []
     file_extension: Optional[str] = ""
-    content: Optional[Any]= None
+    content: Optional[Any] = None
     chunk_size: int = 500
-    chunk_overlap: int= 0
-    documents: Optional[Any]= None
+    chunk_overlap: int = 0
+    documents: Optional[Any] = None
     _commons: Optional[CommonsDep] = None
 
     def __init__(self, **kwargs):
@@ -56,7 +58,6 @@ def compute_documents(self, loader_class):
 
             print("documents", documents)
 
-
         os.remove(tmp_file.name)
 
         text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
@@ -68,6 +69,11 @@ def compute_documents(self, loader_class):
         print(self.documents)
 
     def set_file_vectors_ids(self):
+        """
+        Set the vectors_ids property with the ids of the vectors 
+        that are associated with the file in the vectors table
+        """
+
         commons = common_dependencies() 
         response = (
             commons["supabase"].table("vectors")
@@ -78,32 +84,45 @@ def set_file_vectors_ids(self):
         self.vectors_ids = response.data
         return
 
-    def file_already_exists(self, brain_id):
-        commons = common_dependencies() 
-
+    def file_already_exists(self):
+        """
+        Check if file already exists in vectors table
+        """
         self.set_file_vectors_ids()
 
         print("file_sha1", self.file_sha1)
         print("vectors_ids", self.vectors_ids)
         print("len(vectors_ids)", len(self.vectors_ids))
 
+        # if the file does not exist in vectors then no need to go check in brains_vectors
         if len(self.vectors_ids) == 0:
             return False
-        
-        for vector in self.vectors_ids:
-            response = (
-                commons["supabase"].table("brains_vectors")
-                .select("brain_id, vector_id")
-                .filter("brain_id", "eq", brain_id)
-                .filter("vector_id", "eq", vector['id'])
-                .execute()
-            )
-            print("response.data", response.data)
-            if len(response.data) == 0:
-                return False
-                
+       
         return True
 
+    def file_already_exists_in_brain(self, brain_id):
+        commons = common_dependencies() 
+        self.set_file_vectors_ids()
+        # Check if file exists in that brain
+        response = (
+            commons["supabase"].table("brains_vectors")
+            .select("brain_id, vector_id")
+            .filter("brain_id", "eq", brain_id)
+            .filter("file_sha1", "eq", self.file_sha1)
+            .execute()
+        )
+        print("response.data", response.data)
+        if len(response.data) == 0:
+            return False
+                
+        return True
+  
     def file_is_empty(self):
         return self.file.file._file.tell()  < 1
-    
+    
+    def link_file_to_brain(self, brain: Brain):
+        self.set_file_vectors_ids()
+
+        for vector_id in self.vectors_ids:
+            brain.create_brain_vector(vector_id['id'], self.file_sha1)
+        print(f"Successfully linked file {self.file_sha1} to brain {brain.id}")

backend/models/users.py

@@ -5,24 +5,23 @@
 from pydantic import BaseModel
 
 logger = get_logger(__name__)
+
+
 class User(BaseModel):
     id: UUID
     email: str
     user_openai_api_key: str = None
     requests_count: int = 0
-    user_openai_api_key: str = None
-
 
     # [TODO] Rename the user table and its references to 'user_usage'
-    def create_user( self,date):
+    def create_user(self, date):
 
         commons = common_dependencies()
         logger.info(f"New user entry in db document for user {self.email}")
 
-        return(commons['supabase'].table("users").insert(
+        return (commons['supabase'].table("users").insert(
             {"user_id": self.id, "email": self.email, "date": date, "requests_count": 1}).execute())
 
-
     def get_user_request_stats(self):
         commons = common_dependencies()
         requests_stats = commons['supabase'].from_('users').select(
@@ -43,12 +42,11 @@ def fetch_user_requests_count(self, date):
 
         return userItem["requests_count"]
 
-
     def increment_user_request_count(self, date):
         commons = common_dependencies()
         requests_count = self.fetch_user_requests_count(date) + 1
         logger.info(f"User {self.email} request count updated to {requests_count}")
         commons['supabase'].table("users").update(
-            { "requests_count": requests_count}).match({"user_id": self.id, "date": date}).execute()
+            {"requests_count": requests_count}).match({"user_id": self.id, "date": date}).execute()
         self.requests_count = requests_count
 

backend/parsers/common.py

@@ -31,14 +31,15 @@ async def process_file(
         }
         doc_with_metadata = Document(
             page_content=doc.page_content, metadata=metadata)
+        
         neurons = Neurons(commons=commons)
         created_vector = neurons.create_vector(doc_with_metadata, user_openai_api_key)
         # add_usage(stats_db, "embedding", "audio", metadata={"file_name": file_meta_name,"file_type": ".txt", "chunk_size": chunk_size, "chunk_overlap": chunk_overlap})
 
         created_vector_id = created_vector[0]
 
         brain = Brain(id=brain_id)
-        brain.create_brain_vector(created_vector_id)
+        brain.create_brain_vector(created_vector_id, file.file_sha1)
 
     return
 

backend/parsers/github.py

@@ -15,8 +15,8 @@ async def process_github(commons: CommonsDep, repo, enable_summarization, brain_
     random_dir_name = os.urandom(16).hex()
     dateshort = time.strftime("%Y%m%d")
     loader = GitLoader(
-    clone_url=repo,
-    repo_path="/tmp/" + random_dir_name,
+        clone_url=repo,
+        repo_path="/tmp/" + random_dir_name,
     )
     documents = loader.load()
     os.system("rm -rf /tmp/" + random_dir_name)
@@ -44,21 +44,21 @@ async def process_github(commons: CommonsDep, repo, enable_summarization, brain_
         doc_with_metadata = Document(
             page_content=doc.page_content, metadata=metadata)
 
-        file = File(file_sha1 = compute_sha1_from_content(doc.page_content.encode("utf-8")))
+        file = File(file_sha1=compute_sha1_from_content(doc.page_content.encode("utf-8")))
 
-        exist = file.file_already_exists(brain_id)
-        if not exist:
+        file_exists = file.file_already_exists()
+
+        if not file_exists:
+            print(f"Creating entry for file {file.file_sha1} in vectors...")
             neurons =  Neurons(commons=commons)
             created_vector = neurons.create_vector(doc_with_metadata, user_openai_api_key)
+            print("Created vector sids ", created_vector)
+            print("Created vector for ", doc.metadata["file_name"])
 
-            created_vector_id = created_vector[0]
+        file_exists_in_brain = file.file_already_exists_in_brain(brain_id)
 
+        if not file_exists_in_brain:
+            file.add_file_to_brain(brain_id)
             brain = Brain(id=brain_id)
-            brain.create_brain_vector(created_vector_id)
-
-            print("Created vector for ", doc.metadata["file_name"])
-            # add created_vector x brains in db
-            
-
+            file.link_file_to_brain(brain)
     return {"message": f"✅ Github with {len(documents)} files has been uploaded.", "type": "success"}
-

backend/routes/brain_routes.py

@@ -131,10 +131,13 @@ async def brain_endpoint(
     brain.create_brain()
     default_brain = get_default_user_brain(current_user)
     if default_brain:
-        # create a brain X user entry
+        logger.info(f"Default brain already exists for user {current_user.id}")
         brain.create_brain_user(user_id = current_user.id, rights="Owner", default_brain=False)
     else:
+        logger.info(f"Default brain does not exist for user {current_user.id}. It will be created.")
         brain.create_brain_user(user_id = current_user.id, rights="Owner", default_brain=True)
+
+    
     return {"id": brain.id, "name": brain.name}
 
 # update existing brain

backend/routes/explore_routes.py

@@ -9,8 +9,8 @@
 explore_router = APIRouter()
 
 
-@explore_router.get("/explore", dependencies=[Depends(AuthBearer())], tags=["Explore"])
-async def explore_endpoint(brain_id: UUID = Query(..., description="The ID of the brain"),current_user: User = Depends(get_current_user)):
+@explore_router.get("/explore/", dependencies=[Depends(AuthBearer())], tags=["Explore"])
+async def explore_endpoint(brain_id: UUID = Query(..., description="The ID of the brain"), current_user: User = Depends(get_current_user)):
     """
     Retrieve and explore unique user data vectors.
     """

backend/utils/processors.py

@@ -1,4 +1,5 @@
 
+from models.brains import Brain
 from models.files import File
 from models.settings import CommonsDep
 from parsers.audio import process_audio
@@ -35,20 +36,32 @@
 }
 
 
+def create_response(message, type):
+    return {"message": message, "type": type}
 
 
 async def filter_file(commons: CommonsDep, file: File, enable_summarization: bool, brain_id, openai_api_key):
     await file.compute_file_sha1()
 
     print("file sha1", file.file_sha1)
-    if file.file_already_exists( brain_id):
-        return {"message": f"🤔 {file.file.filename} already exists in brain {brain_id}.", "type": "warning"}
+    file_exists = file.file_already_exists()
+    file_exists_in_brain = file.file_already_exists_in_brain(brain_id)
+
+    if file_exists_in_brain:
+        return create_response(f"🤔 {file.file.filename} already exists in brain {brain_id}.", "warning")
     elif file.file_is_empty():
-        return {"message": f"❌ {file.file.filename} is empty.", "type": "error"}
-    else:
-        if file.file_extension in file_processors:
-            await file_processors[file.file_extension](commons,file, enable_summarization, brain_id ,openai_api_key )
-            return {"message": f"✅ {file.file.filename} has been uploaded to brain {brain_id}.", "type": "success"}
-        else:
-            return {"message": f"❌ {file.file.filename} is not supported.", "type": "error"}
+        return create_response(f"❌ {file.file.filename} is empty.", "error")
+    elif file_exists:
+        file.link_file_to_brain(brain=Brain(id=brain_id))
+        return create_response(f"✅ {file.file.filename} has been uploaded to brain {brain_id}.", "success")
+    
+    if file.file_extension in file_processors:
+        try:
+            await file_processors[file.file_extension](commons, file, enable_summarization, brain_id, openai_api_key)
+            return create_response(f"✅ {file.file.filename} has been uploaded to brain {brain_id}.", "success")
+        except Exception as e:
+            # Add more specific exceptions as needed.
+            print(f"Error processing file: {e}")
+            return create_response(f"⚠️ An error occurred while processing {file.file.filename}.", "error")
 
+    return create_response(f"❌ {file.file.filename} is not supported.", "error")