Generate tags around context

Reviewed-on: #16

.gitea/workflows/deploy.yml

@@ -0,0 +1,56 @@
+name: Create Blog Article if new notes exist
+on:
+    schedule:
+        - cron: "15 3 * * *"
+    push:
+        branches:
+            - master
+jobs:
+    prepare_blog_drafts_and_push:
+        runs-on: ubuntu-latest
+        steps:
+            - name: Checkout repository
+              uses: actions/checkout@v4
+
+            - name: Install dependencies
+              shell: bash
+              run: |
+                  apt update && apt upgrade -y
+                  apt install rustc cargo python-is-python3 pip python3-venv python3-virtualenv libmagic-dev git -y
+                  virtualenv .venv
+                  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
+                  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
+
+            - name: Create Blogs
+              shell: bash
+              run: |
+                  source .venv/bin/activate
+                  python src/main.py

.gitignore

@@ -7,3 +7,4 @@ __pycache__
 pyproject.toml
 .ropeproject
 generated_files/*
+pyright*

requirements.txt

@@ -4,3 +4,5 @@ gitpython
 PyGithub
 chromadb
 langchain-ollama
+PyJWT
+dotenv

src/ai_generators/ollama_md_generator.py

@@ -11,7 +11,13 @@ class OllamaGenerator:
         self.inner_title = inner_title
         self.content = content
         self.response = None
-        self.chroma = chromadb.HttpClient(host="172.18.0.2", port=8000)
+        print("In Class")
+        print(os.environ["CONTENT_CREATOR_MODELS"])
+        try:
+            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.ollama_client = Client(host=ollama_url)
         self.ollama_model = os.environ["EDITOR_MODEL"]
@@ -20,14 +26,14 @@ class OllamaGenerator:
         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 1000 word draft blog for other tech enthusiasts.
+            writing a 3000 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):
@@ -116,14 +122,15 @@ class OllamaGenerator:
         prompt_system = f"""
             You are an editor taking information from {len(self.agent_models)} Software
             Developers and Data experts
-            writing a 3000 word blog for other tech enthusiasts.
+            writing a 3000 word blog article. You like when they use almost no code examples.
-            You like when they use almost no code examples and the
+            You are also Australian. The content may have light comedic elements,
-            voice is in a light comedic tone. You are also Australian
+            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.
             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>
             """
         try:
             query_embed = self.ollama_client.embed(model=self.embed_model, input=prompt_system)['embeddings']
@@ -132,7 +139,9 @@ class OllamaGenerator:
             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 THE MARKDOWN"
+            prompt_human = f"""Generate the final, 3000 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()
@@ -154,9 +163,7 @@ class OllamaGenerator:
         with open(filename, "w") as f:
             f.write(self.generate_markdown())
 
-    def generate_commit_message(self):
+    def generate_system_message(self, prompt_system, prompt_human):
-        prompt_system = "You are a blog creator commiting a piece of content to a central git repo"
-        prompt_human = f"Generate a 5 word git commit message describing {self.response}"
         messages = [("system", prompt_system), ("human", prompt_human),]
-        commit_message = self.llm.invoke(messages).text()
+        ai_message = self.llm.invoke(messages).text()
-        return commit_message
+        return ai_message

src/main.py

@@ -1,7 +1,13 @@
 import ai_generators.ollama_md_generator as omg
 import trilium.notes as tn
 import repo_management.repo_manager as git_repo
+from notifications.n8n import N8NWebhookJwt
 import string,os
+from datetime import datetime
+from dotenv import load_dotenv
+load_dotenv()
+print(os.environ["CONTENT_CREATOR_MODELS"])
+
 
 tril = tn.TrilumNotes()
 
@@ -24,11 +30,51 @@ 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)
+
+
     # Generate commit messages and push to repo
-    commit_message = ai_gen.generate_commit_message()
+    print("Generating Commit Message")
+    git_sytem_prompt = "You are a blog creator commiting a piece of content to a central git repo"
+    git_human_prompt = f"Generate a 5 word git commit message describing {ai_gen.response}. ONLY OUTPUT THE RESPONSE"
+    commit_message = ai_gen.generate_system_message(git_sytem_prompt, git_human_prompt)
     git_user = os.environ["GIT_USER"]
     git_pass = os.environ["GIT_PASS"]
     repo_manager = git_repo.GitRepository("blog/", git_user, git_pass)
+    print("Pushing to Repo")
     repo_manager.create_copy_commit_push(blog_path, os_friendly_title, commit_message)
+
+    # Generate notification for Matrix
+    print("Generating Notification Message")
+    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 100 word
+        summary describing {ai_gen.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']
+    webhook_url = os.environ['N8N_WEBHOOK_URL']
+    notification_string = f"""
+        <h2>{tril_notes[note]['title']}</h2>
+        <h3>Summary</h3>
+        <p>{notification_message}</p>
+        <h3>Branch</h3>
+        <p>{os_friendly_title}</p>
+        <p><a href="{git_branch_url}">Link to Branch</a></p>
+    """
+
+    payload = {
+        "message": f"{notification_string}",
+        "timestamp": datetime.now().isoformat()
+    }
+
+    webhook_client = N8NWebhookJwt(secret_key, webhook_url)
+
+    print("Notifying")
+    n8n_result = webhook_client.send_webhook(payload)
+
+    print(f"N8N response: {n8n_result['status']}")

src/notifications/n8n.py

@@ -0,0 +1,45 @@
+from datetime import datetime, timedelta
+import jwt
+import requests
+from typing import Dict, Optional
+
+class N8NWebhookJwt:
+    def __init__(self, secret_key: str, webhook_url: str):
+        self.secret_key = secret_key
+        self.webhook_url = webhook_url
+        self.token_expiration = datetime.now() + timedelta(hours=1)
+
+    def _generate_jwt_token(self, payload: Dict) -> str:
+        """Generate JWT token with the given payload."""
+        # Include expiration time (optional)
+        payload["exp"] = self.token_expiration.timestamp()
+        encoded_jwt = jwt.encode(
+                    payload,
+                    self.secret_key,
+                    algorithm="HS256",
+                )
+        return encoded_jwt #jwt.decode(encoded_jwt, self.secret_key, algorithms=['HS256'])
+
+    def send_webhook(self, payload: Dict) -> Dict:
+        """Send a webhook request with JWT authentication."""
+        # Generate JWT token
+        token = self._generate_jwt_token(payload)
+
+        # Set headers with JWT token
+        headers = {
+            "Authorization": f"Bearer {token}",
+            "Content-Type": "application/json"
+        }
+
+        # Send POST request
+        response = requests.post(
+            self.webhook_url,
+            json=payload,
+            headers=headers
+        )
+
+        # Handle response
+        if response.status_code == 200:
+            return {"status": "success", "response": response.json()}
+        else:
+            return {"status": "error", "response": response.status_code, "message": response.text}