syntax fixes for retry logic

Reviewed-on: #16

.gitea/workflows/deploy.yml

@@ -1,7 +1,7 @@
 name: Create Blog Article if new notes exist
 on:
     schedule:
-        - cron: "15 3 * * *"
+        - cron: "15 18 * * *"
     push:
         branches:
             - master
@@ -21,29 +21,33 @@ jobs:
                   source .venv/bin/activate
                   pip install --upgrade pip
                   pip install -r requirements.txt
+                  git config --global user.name "Blog Creator"
+                  git config --global user.email "ridgway.infrastructure@gmail.com"
+                  git config --global push.autoSetupRemote true
 
             - name: Create .env
               shell: bash
               run: |
                   echo "TRILIUM_HOST=${{ vars.TRILIUM_HOST }}" > .env
-                  echo "TRILIUM_PORT=${{ vars.TRILIUM_PORT }}" >> .env
-                  echo "TRILIUM_PROTOCOL=${{ vars.TRILIUM_PROTOCOL }}" >> .env
-                  echo "TRILIUM_PASS=${{ secrets.TRILIUM_PASS }}" >> .env
-                  echo "TRILIUM_TOKEN=${{ secrets.TRILIUM_TOKEN }}" >> .env
-                  echo "OLLAMA_PROTOCOL=${{ vars.OLLAMA_PROTOCOL }}" >> .env
-                  echo "OLLAMA_HOST=${{ vars.OLLAMA_HOST }}" >> .env
-                  echo "OLLAMA_PORT=${{ vars.OLLAMA_PORT }}" >> .env
-                  echo "EMBEDDING_MODEL=${{ vars.EMBEDDING_MODEL }}" >> .env
-                  echo "EDITOR_MODEL=${{ vars.EDITOR_MODEL }}" >> .env
-                  echo "CONTENT_CREATOR_MODELS='${{ vars.CONTENT_CREATOR_MODELS }}'" >> .env
-                  echo "GIT_PROTOCOL=${{ vars.GIT_PROTOCOL }}" >> .env
-                  echo "GIT_REMOTE=${{ vars.GIT_REMOTE }}" >> .env
-                  echo "GIT_USER=${{ vars.GIT_USER }}" >> .env
+                  echo "TRILIUM_PORT='${{ vars.TRILIUM_PORT }}'" >> .env
+                  echo "TRILIUM_PROTOCOL='${{ vars.TRILIUM_PROTOCOL }}'" >> .env
+                  echo "TRILIUM_PASS='${{ secrets.TRILIUM_PASS }}'" >> .env
+                  echo "TRILIUM_TOKEN='${{ secrets.TRILIUM_TOKEN }}'" >> .env
+                  echo "OLLAMA_PROTOCOL='${{ vars.OLLAMA_PROTOCOL }}'" >> .env
+                  echo "OLLAMA_HOST='${{ vars.OLLAMA_HOST }}'" >> .env
+                  echo "OLLAMA_PORT='${{ vars.OLLAMA_PORT }}'" >> .env
+                  echo "EMBEDDING_MODEL='${{ vars.EMBEDDING_MODEL }}'" >> .env
+                  echo "EDITOR_MODEL='${{ vars.EDITOR_MODEL }}'" >> .env
+                  export PURE='["${{ vars.CONTENT_CREATOR_MODELS_1 }}", "${{ vars.CONTENT_CREATOR_MODELS_2 }}", "${{ vars.CONTENT_CREATOR_MODELS_3 }}", "${{ vars.CONTENT_CREATOR_MODELS_4 }}"]'
+                  echo "CONTENT_CREATOR_MODELS='$PURE'" >> .env
+                  echo "GIT_PROTOCOL='${{ vars.GIT_PROTOCOL }}'" >> .env
+                  echo "GIT_REMOTE='${{ vars.GIT_REMOTE }}'" >> .env
+                  echo "GIT_USER='${{ vars.GIT_USER }}'" >> .env
                   echo "GIT_PASS='${{ secrets.GIT_PASS }}'" >> .env
                   echo "N8N_SECRET='${{ secrets.N8N_SECRET }}'" >> .env
                   echo "N8N_WEBHOOK_URL='${{ vars.N8N_WEBHOOK_URL }}'" >> .env
-                  echo "CHROMA_HOST=${{ vars.CHROMA_HOST }}" >> .env
-                  echo "CHROMA_PORT=${{ vars.CHROMA_PORT }}" >> .env
+                  echo "CHROMA_HOST='${{ vars.CHROMA_HOST }}'" >> .env
+                  echo "CHROMA_PORT='${{ vars.CHROMA_PORT }}'" >> .env
 
             - name: Create Blogs
               shell: bash

src/ai_generators/ollama_md_generator.py

@@ -1,42 +1,54 @@
-import os, re, json, random, time, string
-from ollama import Client
+import json
+import os
+import random
+import re
+import string
+import time
+from concurrent.futures import ThreadPoolExecutor, TimeoutError
+
 import chromadb
 from langchain_ollama import ChatOllama
+from ollama import Client
 
 
 class OllamaGenerator:
-
     def __init__(self, title: str, content: str, inner_title: str):
         self.title = title
         self.inner_title = inner_title
         self.content = content
         self.response = None
+        print("In Class")
+        print(os.environ["CONTENT_CREATOR_MODELS"])
         try:
-            chroma_port = int(os.environ['CHROMA_PORT'])
+            chroma_port = int(os.environ["CHROMA_PORT"])
         except ValueError as e:
             raise Exception(f"CHROMA_PORT is not an integer: {e}")
-        self.chroma = chromadb.HttpClient(host=os.environ['CHROMA_HOST'], port=chroma_port)
-        ollama_url = f"{os.environ["OLLAMA_PROTOCOL"]}://{os.environ["OLLAMA_HOST"]}:{os.environ["OLLAMA_PORT"]}"
+        self.chroma = chromadb.HttpClient(
+            host=os.environ["CHROMA_HOST"], port=chroma_port
+        )
+        ollama_url = f"{os.environ['OLLAMA_PROTOCOL']}://{os.environ['OLLAMA_HOST']}:{os.environ['OLLAMA_PORT']}"
         self.ollama_client = Client(host=ollama_url)
         self.ollama_model = os.environ["EDITOR_MODEL"]
         self.embed_model = os.environ["EMBEDDING_MODEL"]
         self.agent_models = json.loads(os.environ["CONTENT_CREATOR_MODELS"])
-        self.llm = ChatOllama(model=self.ollama_model, temperature=0.6, top_p=0.5) #This  is the level head in the room
+        self.llm = ChatOllama(
+            model=self.ollama_model, temperature=0.6, top_p=0.5
+        )  # This  is the level head in the room
         self.prompt_inject = f"""
             You are a journalist, Software Developer and DevOps expert
-            writing a 3000 word draft blog article for other tech enthusiasts.
+            writing a 5000 word draft blog article for other tech enthusiasts.
             You like to use almost no code examples and prefer to talk
             in a light comedic tone. You are also Australian
             As this person write this blog as a markdown document.
             The title for the blog is {self.inner_title}.
             Do not output the title in the markdown.
             The basis for the content of the blog is:
-                {self.content}
+                <blog>{self.content}</blog>
             """
 
     def split_into_chunks(self, text, chunk_size=100):
-        '''Split text into chunks of size chunk_size'''
-        words = re.findall(r'\S+', text)
+        """Split text into chunks of size chunk_size"""
+        words = re.findall(r"\S+", text)
 
         chunks = []
         current_chunk = []
@@ -47,18 +59,19 @@ class OllamaGenerator:
             word_count += 1
 
         if word_count >= chunk_size:
-            chunks.append(' '.join(current_chunk))
+            chunks.append(" ".join(current_chunk))
             current_chunk = []
             word_count = 0
 
         if current_chunk:
-            chunks.append(' '.join(current_chunk))
+            chunks.append(" ".join(current_chunk))
 
         return chunks
 
     def generate_draft(self, model) -> str:
-        '''Generate a draft blog post using the specified model'''
-        try:
+        """Generate a draft blog post using the specified model"""
+
+        def _generate():
             # the idea behind this is to make the "creativity" random amongst the content creators
             # contorlling temperature will allow cause the output to allow more "random" connections in sentences
             # Controlling top_p will tighten or loosen the embedding connections made
@@ -67,89 +80,253 @@ class OllamaGenerator:
             temp = random.uniform(0.5, 1.0)
             top_p = random.uniform(0.4, 0.8)
             top_k = int(random.uniform(30, 80))
-            agent_llm = ChatOllama(model=model, temperature=temp, top_p=top_p, top_k=top_k)
+            agent_llm = ChatOllama(
+                model=model, temperature=temp, top_p=top_p, top_k=top_k
+            )
             messages = [
-                ("system", self.prompt_inject),
-                ("human", "make the blog post in a format to be edited easily" )
+                (
+                    "system",
+                    "You are a creative writer specialising in writing about technology",
+                ),
+                ("human", self.prompt_inject),
             ]
             response = agent_llm.invoke(messages)
-            # self.response = self.ollama_client.chat(model=model,
-            #                                         messages=[
-            #         {
-            #             'role': 'user',
-            #             'content': f'{self.prompt_inject}',
-            #         },
-            #     ])
-            #print ("draft")
-            #print (response)
-            return response.text()#['message']['content']
+            return (
+                response.text if hasattr(response, "text") else str(response)
+            )  # ['message']['content']
 
+        # Retry mechanism with 30-minute timeout
+        timeout_seconds = 30 * 60  # 30 minutes
+        max_retries = 3
+
+        for attempt in range(max_retries):
+            try:
+                with ThreadPoolExecutor(max_workers=1) as executor:
+                    future = executor.submit(_generate)
+                    result = future.result(timeout=timeout_seconds)
+                    return result
+            except TimeoutError:
+                print(
+                    f"AI call timed out after {timeout_seconds} seconds on attempt {attempt + 1}"
+                )
+                if attempt < max_retries - 1:
+                    print("Retrying...")
+                    time.sleep(5)  # Wait 5 seconds before retrying
+                    continue
+                else:
+                    raise Exception(
+                        f"AI call failed to complete after {max_retries} attempts with {timeout_seconds} second timeouts"
+                    )
             except Exception as e:
-            raise Exception(f"Failed to generate blog draft: {e}")
+                if attempt < max_retries - 1:
+                    print(f"Attempt {attempt + 1} failed with error: {e}. Retrying...")
+                    time.sleep(5)  # Wait 5 seconds before retrying
+                    continue
+                else:
+                    raise Exception(
+                        f"Failed to generate blog draft after {max_retries} attempts: {e}"
+                    )
 
     def get_draft_embeddings(self, draft_chunks):
-        '''Get embeddings for the draft chunks'''
-        embeds = self.ollama_client.embed(model=self.embed_model, input=draft_chunks)
-        return embeds.get('embeddings', [])
+        """Get embeddings for the draft chunks"""
+        try:
+            # Handle empty draft chunks
+            if not draft_chunks:
+                print("Warning: No draft chunks to embed")
+                return []
+
+            embeds = self.ollama_client.embed(
+                model=self.embed_model, input=draft_chunks
+            )
+            embeddings = embeds.get("embeddings", [])
+
+            # Check if embeddings were generated successfully
+            if not embeddings:
+                print("Warning: No embeddings generated")
+                return []
+
+            return embeddings
+        except Exception as e:
+            print(f"Error generating embeddings: {e}")
+            return []
 
     def id_generator(self, size=6, chars=string.ascii_uppercase + string.digits):
-        return ''.join(random.choice(chars) for _ in range(size))
+        return "".join(random.choice(chars) for _ in range(size))
 
     def load_to_vector_db(self):
-        '''Load the generated blog drafts into a vector database'''
-        collection_name = f"blog_{self.title.lower().replace(" ", "_")}_{self.id_generator()}"
-        collection = self.chroma.get_or_create_collection(name=collection_name)#, metadata={"hnsw:space": "cosine"})
-        #if any(collection.name == collectionname for collectionname in self.chroma.list_collections()):
+        """Load the generated blog drafts into a vector database"""
+        collection_name = (
+            f"blog_{self.title.lower().replace(' ', '_')}_{self.id_generator()}"
+        )
+        collection = self.chroma.get_or_create_collection(
+            name=collection_name
+        )  # , metadata={"hnsw:space": "cosine"})
+        # if any(collection.name == collectionname for collectionname in self.chroma.list_collections()):
         #    self.chroma.delete_collection("blog_creator")
         for model in self.agent_models:
-            print (f"Generating draft from {model} for load into vector database")
-            draft_chunks = self.split_into_chunks(self.generate_draft(model))
-            print(f"generating embeds")
+            print(f"Generating draft from {model} for load into vector database")
+            try:
+                draft_content = self.generate_draft(model)
+                draft_chunks = self.split_into_chunks(draft_content)
+
+                # Skip if no content was generated
+                if not draft_chunks or all(
+                    chunk.strip() == "" for chunk in draft_chunks
+                ):
+                    print(f"Skipping {model} - no content generated")
+                    continue
+
+                print(f"generating embeds for {model}")
                 embeds = self.get_draft_embeddings(draft_chunks)
+
+                # Skip if no embeddings were generated
+                if not embeds:
+                    print(f"Skipping {model} - no embeddings generated")
+                    continue
+
+                # Ensure we have the same number of embeddings as chunks
+                if len(embeds) != len(draft_chunks):
+                    print(
+                        f"Warning: Mismatch between chunks ({len(draft_chunks)}) and embeddings ({len(embeds)}) for {model}"
+                    )
+                    # Truncate or pad to match
+                    min_length = min(len(embeds), len(draft_chunks))
+                    draft_chunks = draft_chunks[:min_length]
+                    embeds = embeds[:min_length]
+                    if min_length == 0:
+                        print(f"Skipping {model} - no valid content/embeddings pairs")
+                        continue
+
                 ids = [model + str(i) for i in range(len(draft_chunks))]
                 chunknumber = list(range(len(draft_chunks)))
                 metadata = [{"model_agent": model} for index in chunknumber]
-            print(f'loading into collection')
-            collection.add(documents=draft_chunks, embeddings=embeds, ids=ids, metadatas=metadata)
+                print(f"loading into collection for {model}")
+                collection.add(
+                    documents=draft_chunks,
+                    embeddings=embeds,
+                    ids=ids,
+                    metadatas=metadata,
+                )
+            except Exception as e:
+                print(f"Error processing model {model}: {e}")
+                # Continue with other models rather than failing completely
+                continue
 
         return collection
 
-
     def generate_markdown(self) -> str:
-
-        prompt_system = f"""
+        prompt_human = f"""
             You are an editor taking information from {len(self.agent_models)} Software
             Developers and Data experts
-            writing a 3000 word blog article. You like when they use almost no code examples.
+            writing a 5000 word blog article. You like when they use almost no code examples.
             You are also Australian. The content may have light comedic elements,
             you are more professional and will attempt to tone these down
-            As this person produce and an amalgamtion of this blog as a markdown document.
+            As this person produce the final version of this blog as a markdown document
+            keeping in mind the context provided by the previous drafts.
+            You are to produce the content not placeholders for further editors
             The title for the blog is {self.inner_title}.
             Do not output the title in the markdown. Avoid repeated sentences
             The basis for the content of the blog is:
-                {self.content}
+                <blog>{self.content}</blog>
             """
+
+        def _generate_final_document():
             try:
-            query_embed = self.ollama_client.embed(model=self.embed_model, input=prompt_system)['embeddings']
+                embed_result = self.ollama_client.embed(
+                    model=self.embed_model, input=prompt_human
+                )
+                query_embed = embed_result.get("embeddings", [])
+                if not query_embed:
+                    print(
+                        "Warning: Failed to generate query embeddings, using empty list"
+                    )
+                    query_embed = [[]]  # Use a single empty embedding as fallback
+            except Exception as e:
+                print(f"Error generating query embeddings: {e}")
+                # Generate empty embeddings as fallback
+                query_embed = [[]]  # Use a single empty embedding as fallback
+
             collection = self.load_to_vector_db()
-            collection_query = collection.query(query_embeddings=query_embed, n_results=100)
+
+            # Try to query the collection, with fallback for empty collections
+            try:
+                collection_query = collection.query(
+                    query_embeddings=query_embed, n_results=100
+                )
                 print("Showing pertinent info from drafts used in final edited edition")
-            pertinent_draft_info = '\n\n'.join(collection.query(query_embeddings=query_embed, n_results=100)['documents'][0])
-            #print(pertinent_draft_info)
-            prompt_human = f"Generate the final document using this information from the drafts: {pertinent_draft_info} - Only output in markdown, do not wrap in markdown tags"
+
+                # Get documents with error handling
+                query_result = collection.query(
+                    query_embeddings=query_embed, n_results=100
+                )
+                documents = query_result.get("documents", [])
+
+                if documents and len(documents) > 0 and len(documents[0]) > 0:
+                    pertinent_draft_info = "\n\n".join(documents[0])
+                else:
+                    print("Warning: No relevant documents found in collection")
+                    pertinent_draft_info = "No relevant information found in drafts."
+
+            except Exception as query_error:
+                print(f"Error querying collection: {query_error}")
+                pertinent_draft_info = (
+                    "No relevant information found in drafts due to query error."
+                )
+            # print(pertinent_draft_info)
+            prompt_system = f"""Generate the final, 5000 word, draft of the blog using this information from the drafts: <context>{pertinent_draft_info}</context>
+                            - Only output in markdown, do not wrap in markdown tags, Only provide the draft not a commentary on the drafts in the context
+                            """
             print("Generating final document")
-            messages = [("system", prompt_system), ("human", prompt_human),]
-            self.response = self.llm.invoke(messages).text()
+            messages = [
+                ("system", prompt_system),
+                ("human", prompt_human),
+            ]
+            response = self.llm.invoke(messages)
+            return response.text if hasattr(response, "text") else str(response)
+
+        try:
+            # Retry mechanism with 30-minute timeout
+            timeout_seconds = 30 * 60  # 30 minutes
+            max_retries = 3
+
+            for attempt in range(max_retries):
+                try:
+                    with ThreadPoolExecutor(max_workers=1) as executor:
+                        future = executor.submit(_generate_final_document)
+                        self.response = future.result(timeout=timeout_seconds)
+                        break  # Success, exit the retry loop
+                except TimeoutError:
+                    print(
+                        f"AI call timed out after {timeout_seconds} seconds on attempt {attempt + 1}"
+                    )
+                    if attempt < max_retries - 1:
+                        print("Retrying...")
+                        time.sleep(5)  # Wait 5 seconds before retrying
+                        continue
+                    else:
+                        raise Exception(
+                            f"AI call failed to complete after {max_retries} attempts with {timeout_seconds} second timeouts"
+                        )
+                except Exception as e:
+                    if attempt < max_retries - 1:
+                        print(
+                            f"Attempt {attempt + 1} failed with error: {e}. Retrying..."
+                        )
+                        time.sleep(5)  # Wait 5 seconds before retrying
+                        continue
+                    else:
+                        raise Exception(
+                            f"Failed to generate markdown after {max_retries} attempts: {e}"
+                        )
+
             # self.response = self.ollama_client.chat(model=self.ollama_model,
             #                                         messages=[
-            #         {
-            #             'role': 'user',
             #             'content': f'{prompt_enhanced}',
             #         },
             #     ])
-            #print ("Markdown Generated")
-            #print (self.response)
-            return self.response#['message']['content']
+            # print ("Markdown Generated")
+            # print (self.response)
+            return self.response  # ['message']['content']
 
         except Exception as e:
             raise Exception(f"Failed to generate markdown: {e}")
@@ -159,6 +336,43 @@ class OllamaGenerator:
             f.write(self.generate_markdown())
 
     def generate_system_message(self, prompt_system, prompt_human):
-        messages = [("system", prompt_system), ("human", prompt_human),]
-        ai_message = self.llm.invoke(messages).text()
+        def _generate():
+            messages = [
+                ("system", prompt_system),
+                ("human", prompt_human),
+            ]
+            response = self.llm.invoke(messages)
+            ai_message = response.text if hasattr(response, "text") else str(response)
             return ai_message
+
+        # Retry mechanism with 30-minute timeout
+        timeout_seconds = 30 * 60  # 30 minutes
+        max_retries = 3
+
+        for attempt in range(max_retries):
+            try:
+                with ThreadPoolExecutor(max_workers=1) as executor:
+                    future = executor.submit(_generate)
+                    result = future.result(timeout=timeout_seconds)
+                    return result
+            except TimeoutError:
+                print(
+                    f"AI call timed out after {timeout_seconds} seconds on attempt {attempt + 1}"
+                )
+                if attempt < max_retries - 1:
+                    print("Retrying...")
+                    time.sleep(5)  # Wait 5 seconds before retrying
+                    continue
+                else:
+                    raise Exception(
+                        f"AI call failed to complete after {max_retries} attempts with {timeout_seconds} second timeouts"
+                    )
+            except Exception as e:
+                if attempt < max_retries - 1:
+                    print(f"Attempt {attempt + 1} failed with error: {e}. Retrying...")
+                    time.sleep(5)  # Wait 5 seconds before retrying
+                    continue
+                else:
+                    raise Exception(
+                        f"Failed to generate system message after {max_retries} attempts: {e}"
+                    )

src/main.py

@@ -6,6 +6,7 @@ import string,os
 from datetime import datetime
 from dotenv import load_dotenv
 load_dotenv()
+print(os.environ["CONTENT_CREATOR_MODELS"])
 
 
 tril = tn.TrilumNotes()
@@ -29,7 +30,7 @@ for note in tril_notes:
     ai_gen = omg.OllamaGenerator(os_friendly_title,
                                  tril_notes[note]['content'],
                                  tril_notes[note]['title'])
-    blog_path = f"/blog_creator/generated_files/{os_friendly_title}.md"
+    blog_path = f"generated_files/{os_friendly_title}.md"
     ai_gen.save_to_file(blog_path)
 
 
@@ -49,9 +50,10 @@ for note in tril_notes:
     git_branch_url = f'https://git.aridgwayweb.com/armistace/blog/src/branch/{os_friendly_title}/src/content/{os_friendly_title}.md'
     n8n_system_prompt = f"You are a blog creator notifiying the final editor of the final creation of blog available at {git_branch_url}"
     n8n_prompt_human = f"""
-        Generate an informal 150 word
+        Generate an informal 100 word
         summary describing {ai_gen.response}.
-        Don't address it or use names. ONLY OUTPUT THE RESPONSE
+        Don't address it or use names. ONLY OUTPUT THE RESPONSE.
+        ONLY OUTPUT IN PLAINTEXT STRIP ALL MARKDOWN
         """
     notification_message = ai_gen.generate_system_message(n8n_system_prompt, n8n_prompt_human)
     secret_key = os.environ['N8N_SECRET']

src/repo_management/repo_manager.py

@@ -1,8 +1,11 @@
-import os, shutil
+import os
+import shutil
 from urllib.parse import quote
+
 from git import Repo
 from git.exc import GitCommandError
 
+
 class GitRepository:
     # This is designed to be transitory it will desctruvtively create the repo at repo_path
     # if you have uncommited changes you can kiss them goodbye!
@@ -11,8 +14,8 @@ class GitRepository:
     def __init__(self, repo_path, username=None, password=None):
         git_protocol = os.environ["GIT_PROTOCOL"]
         git_remote = os.environ["GIT_REMOTE"]
-        #if username is not set we don't need parse to the url
-        if username==None or password == None:
+        # if username is not set we don't need parse to the url
+        if username == None or password == None:
             remote = f"{git_protocol}://{git_remote}"
         else:
             # of course if it is we need to parse and escape it so that it
@@ -39,7 +42,7 @@ class GitRepository:
             print(f"Cloning failed: {e}")
             return False
 
-    def fetch(self, remote_name='origin', ref_name='main'):
+    def fetch(self, remote_name="origin", ref_name="main"):
         """Fetch updates from a remote repository with authentication"""
         try:
             self.repo.remotes[remote_name].fetch(ref_name=ref_name)
@@ -48,7 +51,7 @@ class GitRepository:
             print(f"Fetching failed: {e}")
             return False
 
-    def pull(self, remote_name='origin', ref_name='main'):
+    def pull(self, remote_name="origin", ref_name="main"):
         """Pull updates from a remote repository with authentication"""
         print("Pulling Latest Updates (if any)")
         try:
@@ -62,18 +65,6 @@ class GitRepository:
         """List all branches in the repository"""
         return [branch.name for branch in self.repo.branches]
 
-
-    def create_and_switch_branch(self, branch_name, remote_name='origin', ref_name='main'):
-        """Create a new branch in the repository with authentication."""
-        try:
-            print(f"Creating Branch {branch_name}")
-            # Use the same remote and ref as before
-            self.repo.git.branch(branch_name)
-        except GitCommandError:
-            print("Branch already exists switching")
-            # ensure remote commits are pulled into local
-        self.repo.git.checkout(branch_name)
-
     def add_and_commit(self, message=None):
         """Add and commit changes to the repository."""
         try:
@@ -91,12 +82,27 @@ class GitRepository:
             print(f"Commit failed: {e}")
             return False
 
-    def create_copy_commit_push(self, file_path, title, commit_messge):
-        self.create_and_switch_branch(title)
+    def create_copy_commit_push(self, file_path, title, commit_message):
+        # Check if branch exists remotely
+        remote_branches = [
+            ref.name.split("/")[-1] for ref in self.repo.remotes.origin.refs
+        ]
 
+        if title in remote_branches:
+            # Branch exists remotely, checkout and pull
+            self.repo.git.checkout(title)
             self.pull(ref_name=title)
-        shutil.copy(f"{file_path}", f"{self.repo_path}src/content/")
+        else:
+            # New branch, create from main
+            self.repo.git.checkout("-b", title, "origin/main")
 
-        self.add_and_commit(f"'{commit_messge}'")
+        # Ensure destination directory exists
+        dest_dir = f"{self.repo_path}src/content/"
+        os.makedirs(dest_dir, exist_ok=True)
 
-        self.repo.git.push()
+        # Copy file
+        shutil.copy(f"{file_path}", dest_dir)
+
+        # Commit and push
+        self.add_and_commit(commit_message)
+        self.repo.git.push("--set-upstream", "origin", title)