initial commit

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.11
+
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY app/requirements.txt /app/
+
+
+RUN python -m venv /venv && \
+    /venv/bin/pip install --upgrade pip && \
+    /venv/bin/pip install -r /app/requirements.txt
+    
+COPY . .
+
+ENV PATH="/venv/bin:$PATH"
+
+EXPOSE 8000
+
+ENTRYPOINT [ "uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "2" ]

app/main.py

@@ -0,0 +1,147 @@
+from apify_client import ApifyClient
+from fastapi import FastAPI
+from astrapy import DataAPIClient
+
+from groq import Groq
+from langchain.chat_models import init_chat_model
+from langchain_core.messages import HumanMessage, SystemMessage
+from langchain_core.vectorstores import InMemoryVectorStore
+from langchain_core.documents import Document
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders import UnstructuredMarkdownLoader
+from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings
+from langchain import hub
+from langgraph.graph import START, StateGraph
+
+from pydantic.main import BaseModel
+from typing_extensions import List, TypedDict
+
+from transformers import pipeline
+
+import os
+import dotenv
+
+dotenv.load_dotenv()
+
+client = ApifyClient(os.getenv("APIFY_API_TOKEN"))
+dbclient = DataAPIClient(os.getenv("ASTRA_DB_TOKEN"))
+db = dbclient.get_database_by_api_endpoint(
+  "https://654d738f-1326-4e94-a2a0-cf79bd1ac826-us-east-2.apps.astra.datastax.com"
+)
+client = Groq()
+# llm = init_chat_model("deepseek-r1-distill-llama-70b", model_provider="groq", api_key=os.getenv("GROQ_API_KEY"))
+
+print(f"Connected to Astra DB: {db.list_collection_names()}")
+
+coll_cursor = db.list_collections()
+cursor = db.get_collection("posts")
+
+app = FastAPI()
+
+@app.get("/fetch/{username}/{posts}")
+async def root(username: str, posts: int):
+    run_input = {
+        "directUrls": [f"https://www.instagram.com/{username}/"],
+        "resultsType": "posts",
+        "resultsLimit": posts,
+        "searchType": "hashtag",
+        "searchLimit": 1,
+        "addParentData": False,
+    }
+
+    run = client.actor("shu8hvrXbJbY3Eb9W").call(run_input=run_input)
+    for item in client.dataset(run["defaultDatasetId"]).iterate_items():
+        #print(item)
+        #print(type(item))
+        result = cursor.find_one({"id": item["id"]})
+
+        if (result == None):
+            cursor.insert_one(item, vectorize=item['id'])
+        else:
+            print(f"Post is cached already! ({item['id']})")
+ 
+class Query(BaseModel):
+    question: str
+    
+@app.get("/chat/{username}")
+async def chat(username: str, request: Query):
+    results = list(cursor.find({"ownerUsername": username}, projection={"type": True, "caption": True, "commentsCount": True, "alt": True, "likesCount": True, "ownerFullName": True, "videoDuration": True, "videoViewCount": True, "videoPlayCount": True}))
+    knowledge = []
+    if not results:  
+        await root(username, 2) 
+        results = list(cursor.find({"ownerUsername": username}))  
+    if results:
+        for doc in results:
+            knowledge.append(doc)
+    else:
+        return "No posts found even after fetching."
+        
+    # print(knowledge)
+
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {
+                "role": "system",
+                "content": f"you will solve the users queries about social media with your data {knowledge} hide any calculations you perform."
+            },
+            {
+                "role": "user",
+                "content": f"{request}",
+            }
+        ],
+    
+        model="llama-3.3-70b-versatile",
+        temperature=0.7,
+        max_completion_tokens=1024,
+        top_p=1,
+        stop=None,
+        stream=False,
+    )
+    
+    return (chat_completion.choices[0].message.content)
+    
+from statistics import mean
+
+sentiment_pipeline = pipeline("sentiment-analysis")
+
+@app.get("/analysis/{username}")
+async def analysis(username: str):
+    results = list(cursor.find({"ownerUsername": username}, projection={"latestComments": True}))
+    texts = [comment["text"] for doc in results for comment in doc.get("latestComments", []) if comment["text"].strip()]
+    
+    if not texts:
+        return {"error": "No valid comments found"}
+    
+    sentiment_scores = sentiment_pipeline(texts)
+
+    positive_scores = [s["score"] for s in sentiment_scores if s["label"] == "POSITIVE"]
+    negative_scores = [s["score"] for s in sentiment_scores if s["label"] == "NEGATIVE"]
+
+    scores = {
+        "average_positive_sentiment": mean(positive_scores) if positive_scores else 0,
+        "count_positive": len(positive_scores),
+        "average_negative_sentiment": mean(negative_scores) if negative_scores else 0,
+        "count_negative": len(negative_scores)
+    }
+    
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {
+                "role": "system",
+                "content": f"Help the user interpret the sentiment score of their comments be conscise and clear and straight to the point"
+            },
+            {
+                "role": "user",
+                "content": f"{scores}",
+            }
+        ],
+    
+        model="llama-3.3-70b-versatile",
+        temperature=0.7,
+        max_completion_tokens=1024,
+        top_p=1,
+        stop=None,
+        stream=False,
+    )
+    
+    return (chat_completion.choices[0].message.content)

app/requirements.txt

@@ -0,0 +1,118 @@
+aiohappyeyeballs==2.6.1
+aiohttp==3.11.14
+aiosignal==1.3.2
+annotated-types==0.7.0
+anyio==4.9.0
+apify==2.4.0
+apify_client==1.9.2
+apify_fingerprint_datapoints==0.0.2
+apify_shared==1.3.2
+astrapy==1.5.2
+attrs==25.3.0
+Brotli==1.1.0
+browserforge==1.2.3
+cachetools==5.5.2
+certifi==2025.1.31
+cffi==1.17.1
+charset-normalizer==3.4.1
+click==8.1.8
+colorama==0.4.6
+crawlee==0.6.5
+cryptography==44.0.2
+dataclasses-json==0.6.7
+deprecation==2.1.0
+distro==1.9.0
+dnspython==2.7.0
+email_validator==2.2.0
+eval_type_backport==0.2.2
+fastapi==0.115.11
+fastapi-cli==0.0.7
+filelock==3.18.0
+frozenlist==1.5.0
+fsspec==2025.3.0
+groq==0.20.0
+h11==0.14.0
+h2==4.2.0
+hpack==4.1.0
+httpcore==1.0.7
+httptools==0.6.4
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.29.3
+hyperframe==6.1.0
+idna==3.10
+Jinja2==3.1.6
+jsonpatch==1.33
+jsonpointer==3.0.0
+langchain==0.3.21
+langchain-community==0.3.20
+langchain-core==0.3.46
+langchain-groq==0.3.0
+langchain-text-splitters==0.3.7
+langgraph==0.3.18
+langgraph-checkpoint==2.0.21
+langgraph-prebuilt==0.1.3
+langgraph-sdk==0.1.58
+langsmith==0.3.18
+lazy-object-proxy==1.10.0
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+mdurl==0.1.2
+more-itertools==10.6.0
+mpmath==1.3.0
+msgpack==1.1.0
+multidict==6.2.0
+mypy-extensions==1.0.0
+networkx==3.4.2
+numpy==2.2.4
+orjson==3.10.15
+packaging==24.2
+pillow==11.1.0
+propcache==0.3.0
+psutil==7.0.0
+pycparser==2.22
+pydantic==2.10.6
+pydantic-settings==2.6.1
+pydantic_core==2.27.2
+pyee==13.0.0
+Pygments==2.19.1
+pymongo==4.11.3
+python-dotenv==1.0.1
+python-multipart==0.0.20
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+requests-file==2.1.0
+requests-toolbelt==1.0.0
+rich==13.9.4
+rich-toolkit==0.13.2
+safetensors==0.5.3
+setuptools==77.0.3
+shellingham==1.5.4
+sniffio==1.3.1
+sortedcollections==2.1.0
+sortedcontainers==2.4.0
+SQLAlchemy==2.0.39
+starlette==0.46.1
+sympy==1.13.1
+tenacity==9.0.0
+tldextract==5.1.3
+tokenizers==0.21.1
+toml==0.10.2
+torch==2.6.0
+torchaudio==2.6.0
+torchvision==0.21.0
+tqdm==4.67.1
+transformers==4.49.0
+typer==0.15.2
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+urllib3==2.3.0
+uuid6==2024.7.10
+uvicorn==0.34.0
+uvloop==0.21.0
+watchfiles==1.0.4
+websockets==15.0.1
+yarl==1.18.3
+zstandard==0.23.0