Merge pull request #37 from x-isopod-x/dev/isopod/summarizer

feat: Summarizer FastAPI tool

servers/summarizer-tool/README.md

@@ -0,0 +1,37 @@
+# 📚 Local Summarizer Agent
+
+This FastAPI server acts to summarize a given chunk of text.
+
+It is assumed that you are running an ollama instance in an adjacent container with the default port available.
+
+## 📦 Endpoints
+### POST /summarize/text
+Summarizes the given block of text
+
+📥 Request
+
+Body: 
+```
+{
+    'text':'Your blob of text here. It can be unlimited, but is recommended to be within the context window of the LLM you are asking for a summary from.'
+}
+```
+
+📤 Response:
+
+```
+{
+    "status": "success",
+    "summary": "A summary of your text."
+}
+```
+
+### POST /summarize/chat
+Not yet implemented. Summarizes an exported Open WebUI chat JSON blob.
+
+## 🧩 Environment Variables
+|Name|Description|Default|
+|---|---|---|
+|MODEL|The name of the model you are trying to reference. Should match the model in your ollama instance. | llama3|
+|MODEL_URL|The URL path to the model you are trying to access.|http://host.docker.internal:11434|
+

servers/summarizer-tool/docker-compose.yml

@@ -0,0 +1,22 @@
+services:
+  summarizer:
+    container_name: summarizer
+    image: python:3-slim
+    ports:
+      - 16000:8000
+    restart: unless-stopped
+    environment:
+      - MODEL=llama3
+      - MODEL_URL=http://host.docker.internal:11434
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    volumes:
+      - .:/app
+    entrypoint: >
+      sh -c "
+        apt update && 
+        apt install -y git &&
+        cd /app &&
+        pip install -r ./requirements.txt &&
+        fastapi run
+      "

servers/summarizer-tool/main.py

@@ -0,0 +1,28 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from .summarizers.text_summarizer import TextSummarizer
+
+app = FastAPI(
+    title="Summarizing Server",
+    version="1.0.0",
+    description="Leverages an LLM to summarize data",  
+)
+
+summarizers = {
+    'TEXT':TextSummarizer()
+}
+
+
+class TextRequest(BaseModel):
+    text: str
+
+@app.post("/summarize/text")
+def summarize_text(data: TextRequest):
+    try:
+        result = summarizers['TEXT'].summarize(data.text)
+        if 'content' in result:
+            return {"status": "success", "summary":result['content']}
+        else:
+            raise HTTPException(status_code=500, detail=str(result['error']))
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

servers/summarizer-tool/requirements.txt

@@ -0,0 +1,38 @@
+annotated-types==0.7.0
+anyio==4.9.0
+certifi==2025.1.31
+charset-normalizer==3.4.1
+click==8.1.8
+dnspython==2.7.0
+email_validator==2.2.0
+fastapi==0.115.12
+fastapi-cli==0.0.7
+h11==0.14.0
+httpcore==1.0.8
+httptools==0.6.4
+httpx==0.28.1
+idna==3.10
+Jinja2==3.1.6
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+mdurl==0.1.2
+pydantic==2.11.3
+pydantic_core==2.33.1
+Pygments==2.19.1
+python-dotenv==1.1.0
+python-multipart==0.0.20
+PyYAML==6.0.2
+requests==2.32.3
+rich==14.0.0
+rich-toolkit==0.14.1
+shellingham==1.5.4
+sniffio==1.3.1
+starlette==0.46.2
+typer==0.15.2
+typing-inspection==0.4.0
+typing_extensions==4.13.2
+urllib3==2.4.0
+uvicorn==0.34.1
+uvloop==0.21.0
+watchfiles==1.0.5
+websockets==15.0.1

servers/summarizer-tool/summarizers/base.py

@@ -0,0 +1,7 @@
+from abc import ABC, abstractmethod
+
+class BaseSummarizer(ABC):
+    @abstractmethod
+    def summarize(self, data: str) -> dict:
+        """Summarize data"""
+        pass

servers/summarizer-tool/summarizers/text_summarizer.py

@@ -0,0 +1,57 @@
+import requests
+from .base import BaseSummarizer
+import os
+
+MODEL_URL=os.environ.get('MODEL_URL')
+MODEL=os.environ.get('MODEL')
+SUMMARIZE_PROMPT = """You are the summarizing agent in a long chain of agents.
+It is your job to responsibly capture the entirety of what is being described in incoming documents.
+You can scrap small details, but you must make sure to hit all the major points.
+These documents will be used in RAG down the line.
+
+
+For example, given the following text:
+"I've got updates on the tiny brains if\nyou are not familiar with brain\norganoids they are tiny human brains\nthat we can grow from stem cells you can\ngrow them in a literal jar if you want\nto but you can also hook them up to a\ncomputer or llm since a company called\nfinal spark decided to release brain\norganoid computation for industrial use\n"
+
+You would respond with
+
+"The speaker is discussing human brain stem cells being grown for industrial use."
+
+Another example:
+hi, i'\''m isopod (formerly hornet)\n \ni'\''m a software engineer\n \ni write code, make costumes, and write music
+
+You would respond with
+Isopod, formerly hornet, is a software engineer who makes costumes and writes music.
+
+You always sanitize data. You always remove \n. You never mention yourself in your summaries. You never infer, only summarize what is presented. You never describe the text as summarized: you always just give the summary.
+"""
+
+class TextSummarizer(BaseSummarizer):
+    def summarize(self, data):
+        payload = {
+            "model":MODEL,
+            "system": SUMMARIZE_PROMPT,
+            "prompt":data,
+            "stream":False,
+            "options":{
+                "temperature":0.5
+            }
+        }
+        url = MODEL_URL + '/api/generate'
+        result = requests.post(url=url, json=payload)
+        if result.status_code == 200:
+            json_data = result.json()
+            if 'response' in json_data:
+                return {
+                    'type': 'text',
+                    'source': url,
+                    'content': json_data['response']
+                }
+        print(result.content)
+        return {
+            'type': 'text',
+            'source': url,
+            'error': result.status_code   
+        }
+
+