Oracle and smolagent

Oracle/DataSmolAgent.py

@@ -0,0 +1,116 @@
+import pandas as pd
+import numpy as np
+from smolagents import HfApiModel,tool,CodeAgent
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+@tool
+def clean_data(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Clean the DataFrame by stripping whitespace from column names and dropping rows that are completely empty.
+
+    Args:
+        df (pd.DataFrame): The input DataFrame containing the raw data.
+
+    Returns:
+        pd.DataFrame: A cleaned DataFrame with stripped column names and without completely empty rows.
+    """
+    df.columns = df.columns.str.strip()
+    df = df.dropna(how="all")
+    return df
+
+@tool
+def extract_features(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Dynamically extract features from the DataFrame.
+    
+    For numeric columns:
+      - If all values are non-negative, a log-transformed version is created.
+      
+    For columns that appear to be dates:
+      - Year, month, and day are extracted.
+      
+    For non-numeric, non-date columns:
+      - They are encoded as categorical numeric codes.
+    
+    Args:
+        df (pd.DataFrame): The input DataFrame containing the raw data.
+        
+    Returns:
+        pd.DataFrame: The DataFrame updated with new dynamically engineered features.
+    """
+    # Numeric columns: log transformation
+    numeric_cols = df.select_dtypes(include=[np.number]).columns.to_list()
+    for col in numeric_cols:
+        if (df[col] >= 0).all():
+            df[f"log_{col}"] = np.log(df[col] + 1)
+
+    # Date-like columns extraction
+    for col in df.columns:
+        if "date" in col.lower() or "time" in col.lower():
+            try:
+                df[col] = pd.to_datetime(df[col], errors='coerce')
+                df[f"{col}_year"] = df[col].dt.year
+                df[f"{col}_month"] = df[col].dt.month
+                df[f"{col}_day"] = df[col].dt.day
+            except Exception:
+                pass
+
+    # Non-numeric processing: encode as categorical numeric codes.
+    non_numeric = df.select_dtypes(include=["object"]).columns.to_list()
+    valid_cat = []
+    for col in non_numeric:
+        try:
+            pd.to_datetime(df[col], errors='raise')
+        except Exception:
+            valid_cat.append(col)
+    for col in valid_cat:
+        df[f"{col}_cat"] = df[col].astype("category").cat.codes             
+    
+    return df   
+
+@tool
+def save_to_csv(df: pd.DataFrame, filename: str = "output.csv") -> str:
+    """
+    Save the DataFrame to a CSV file and return the file path.
+
+    Args:
+        df (pd.DataFrame): The DataFrame to save.
+        filename (str): The name of the output CSV file.
+
+    Returns:
+        str: The file path of the saved CSV.
+    """
+    df.to_csv(filename, index=False)
+    return filename
+
+class DataSmolAgent(CodeAgent):
+    """
+    A data processing agent that cleans and extracts features from the provided DataFrame.
+    """
+    def __init__(self, df: pd.DataFrame):
+        self.df = df
+        self.tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-1.7B-Instruct")
+        self.model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM2-1.7B-Instruct")
+        super().__init__(
+            tools=[
+                clean_data,
+                extract_features,
+                save_to_csv,  # Added save_to_csv tool
+            ],
+            model=self.model,
+            additional_authorized_imports=["pandas", "numpy"]
+        )
+
+    def run(self, prompt: str, output_csv: bool = False) -> pd.DataFrame:
+        # Run the agent with the provided DataFrame
+        clean_output = self.tools["clean_data"](df=self.df)
+        self.df = clean_output.result if hasattr(clean_output, "result") else clean_output
+
+        features_output = self.tools["extract_features"](df=self.df)
+        self.df = features_output.result if hasattr(features_output, "result") else features_output
+
+        if output_csv:
+            csv_output = self.tools["save_to_csv"](df=self.df, filename="processed_output.csv")
+            print(f"CSV saved at: {csv_output}")
+
+        return self.df

Oracle/SmolLM.py

@@ -0,0 +1,29 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+class SmolLM:
+    def __init__(self, model_path="HuggingFaceTB/SmolLM2-1.7B-Instruct"):
+        self.available = True
+        try:
+            print(f"[INFO] Loading model tokenizer from {model_path}")
+            self.tokenizer = AutoTokenizer.from_pretrained(model_path)
+            print(f"[INFO] Loading model from {model_path}")
+            self.model = AutoModelForCausalLM.from_pretrained(model_path)
+            print("[INFO] Model loaded successfully")
+        except Exception as e:
+            print(f"[ERROR] Failed to load model '{model_path}': {e}")
+            self.available = False
+
+    def predict(self, prompt):
+        if not self.available:
+            print("[WARN] LLama model unavailable, returning default weight 0.5")
+            return "0.5"
+        try:
+            print(f"[INFO] Generating response for prompt: {prompt[:100]}...", flush=True)
+            inputs = self.tokenizer(prompt, return_tensors="pt", truncation=True, max_length=512)
+            outputs = self.model.generate(**inputs, max_length=150, num_return_sequences=1)
+            response = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
+            print(f"[INFO] Generated response: {response[:100]}...", flush=True)
+            return response
+        except Exception as e:
+            print(f"[ERROR] LLama model inference failed: {e}")
+            return "0.5"

Oracle/deepfundingoracle.py

@@ -0,0 +1,285 @@
+"""
+DeepFunding Oracle:
+This script dynamically loads dependency data and for each repository URL:
+  • Fetches GitHub features (stars, forks, watchers, open issues, pull requests, activity) using the GitHub API.
+  • Uses the LLama model to analyze parent-child behavior (based on the fetched features and parent info)
+    and returns a base weight (0-1) for the repository.
+  • Trains a RandomForest regressor on these features (with the base weight as the target) to predict a final weight.
+The output submission CSV has three columns: repo, parent, and final_weight.
+"""
+
+from io import StringIO
+import os
+import warnings
+import csv
+import re
+import requests
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+import time
+import threading
+import logging
+import concurrent.futures
+import signal
+from tqdm import tqdm
+import sys
+
+from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.metrics import mean_squared_error
+
+from Oracle.SmolLM import SmolLM
+
+warnings.filterwarnings("ignore")
+
+# Configure logging to file and console
+logging.basicConfig(
+    handlers=[
+        logging.FileHandler("deepfundingoracle.log"),
+        logging.StreamHandler(sys.stdout)
+    ],
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s"
+)
+
+##############################
+# Enhanced GitHub API helper: Fetch repository metrics
+##############################
+def fetch_repo_metrics(repo_url):
+    """
+    Fetch GitHub metrics (stars, forks, watchers, open issues, pull requests, and activity) given a repository URL.
+    Assumes repo_url is in the form "https://github.com/owner/repo".
+    """
+    try:
+        # Extract owner and repo name
+        m = re.search(r"github\.com/([^/]+)/([^/]+)", repo_url)
+        if not m:
+            return {"stargazers_count": 0, "forks_count": 0, "watchers_count": 0, "open_issues_count": 0, "pulls_count": 0, "activity": 0}
+        owner, repo_name = m.group(1), m.group(2)
+        api_url = f"https://api.github.com/repos/{owner}/{repo_name}"
+        headers = {}
+
+        token = os.environ.get("GITHUB_API_TOKEN", "")
+        if token: headers["Authorization"] = f"token {token}"
+        r = requests.get(api_url, headers=headers)
+        if r.status_code == 200:
+            data = r.json()
+            pulls_url = data.get("pulls_url", "").replace("{\/*state}", "")
+            pulls_count = len(requests.get(pulls_url, headers=headers).json()) if pulls_url else 0
+            activity = data.get("updated_at", "")
+            return {
+                "stargazers_count": data.get("stargazers_count", 0),
+                "forks_count": data.get("forks_count", 0),
+                "watchers_count": data.get("watchers_count", 0),
+                "open_issues_count": data.get("open_issues_count", 0),
+                "pulls_count": pulls_count,
+                "activity": activity,
+                "owner": owner,
+                "repo_name": repo_name,
+                "token": token
+            }
+        else:
+            return {"stargazers_count": 0, "forks_count": 0, "watchers_count": 0, "open_issues_count": 0, "pulls_count": 0, "activity": 0}
+    except Exception:
+        return {"stargazers_count": 0, "forks_count": 0, "watchers_count": 0, "open_issues_count": 0, "pulls_count": 0, "activity": 0}
+
+
+##############################
+# Enhanced Feature Extraction
+##############################
+def load_data(file):
+    """
+    Dynamically load the dependency data CSV from the uploaded file.
+    Expects at least "repo" and "parent" columns.
+    """
+    try:
+        print("[INFO] Loading data from uploaded file...")
+        start_time = time.time()
+        # Read the uploaded file directly into a DataFrame
+        df = pd.read_csv(file)
+        end_time = time.time()
+        print(f"[INFO] Data loaded successfully in {end_time - start_time:.2f} seconds.")
+        return df
+    except Exception as e:
+        print("[ERROR] Error loading data:", e)
+        return None
+
+def fetch_github_features(df):
+    """
+    For each row, using the repo URL, call the GitHub API to fetch:
+      stars, forks, watchers, open issues, pull requests, activity, and contributors count.
+    Adds these as new columns to the DataFrame.
+    """
+    print("[INFO] Fetching GitHub features for repositories...")
+    start_time = time.time()
+    stars_list = []
+    forks_list = []
+    watchers_list = []
+    issues_list = []
+    pulls_list = []
+    activity_list = []
+    contributors_list = []
+
+    for idx, row in df.iterrows():
+        repo_url = row.get("repo", "")
+        print(f"[INFO] Processing repository {idx + 1}/{len(df)}: {repo_url}")
+        features = fetch_repo_metrics(repo_url)
+        stars_list.append(features["stargazers_count"])
+        forks_list.append(features["forks_count"])
+        watchers_list.append(features["watchers_count"])
+        issues_list.append(features["open_issues_count"])
+        pulls_list.append(features["pulls_count"])
+        activity_list.append(features["activity"])
+
+        # Fetch contributors count
+        try:
+            contributors_url = f"https://api.github.com/repos/{features['owner']}/{features['repo_name']}/contributors"
+            headers = {"Authorization": f"token {features['token']}"}
+            contributors_response = requests.get(contributors_url, headers=headers)
+            if contributors_response.status_code == 200:
+                contributors_list.append(len(contributors_response.json()))
+            else:
+                contributors_list.append(0)
+        except Exception:
+            contributors_list.append(0)
+
+    df["stars"] = stars_list
+    df["forks"] = forks_list
+    df["watchers"] = watchers_list
+    df["open_issues"] = issues_list
+    df["pulls"] = pulls_list
+    df["activity"] = activity_list
+    df["contributors"] = contributors_list
+
+    end_time = time.time()
+    print(f"[INFO] GitHub features fetched successfully in {end_time - start_time:.2f} seconds.")
+    return df
+
+def timeout_handler(signum, frame):
+    raise TimeoutError("LLama model prediction timed out.")
+
+def assign_base_weight(df):
+    print("[INFO] Starting base weight assignment using LLama model...", flush=True)
+    logging.info("[INFO] Assigning base weights using LLama model...")
+    start_time = time.time()
+    llama = SmolLM()
+    base_weights = []
+
+    for idx, row in tqdm(df.iterrows(), total=len(df), desc="Assigning weights"):
+        repo = row.get("repo", "")
+        print(f"[INFO] Assigning weight for repository {idx + 1}/{len(df)}: {repo}", flush=True)
+        logging.info(f"[INFO] Processing repository {idx + 1}/{len(df)}: {repo}")
+        parent = row.get("parent", "")
+        stars = row.get("stars", 0)
+        forks = row.get("forks", 0)
+        watchers = row.get("watchers", 0)
+        issues = row.get("open_issues", 0)
+        pulls = row.get("pulls", 0)
+        activity = row.get("activity", "")
+        prompt = (
+            f"Repository: {repo}\n"
+            f"GitHub Metrics: {stars} stars, {forks} forks, {watchers} watchers, {issues} open issues, {pulls} pull requests, activity: {activity}.\n"
+            f"Parent or dependency: {parent}\n\n"
+            "Based on these features, assign a dependency weight between 0 and 1 for the repository "
+            "that reflects how influential the repository is as a source relative to its parent. "
+            "Only output the numeric value."
+        )
+        try:
+            print(f"[INFO] Sending prompt to LLama model for repo: {repo}", flush=True)
+            start_llama_time = time.time()
+            response = llama.predict(prompt)
+            weight = float(''.join([c for c in response if c.isdigit() or c == '.']))
+            weight = min(max(weight, 0), 1)
+            end_llama_time = time.time()
+            print(f"[INFO] Received weight {weight} for {repo} in {end_llama_time - start_llama_time:.2f} seconds.", flush=True)
+            logging.info(f"[INFO] Processed repository {repo} in {end_llama_time - start_llama_time:.2f} seconds. Weight: {weight}")
+        except Exception as e:
+            print(f"[ERROR] Failed to process repository {repo}: {e}", flush=True)
+            logging.error(f"[ERROR] Failed to process repository {repo}: {e}")
+            weight = 0.5  # Default weight in case of failure
+        base_weights.append(weight)
+        print(f"[PROGRESS] Finished {idx + 1}/{len(df)} repositories.", flush=True)
+
+    df["base_weight"] = base_weights
+    end_time = time.time()
+    print(f"[INFO] Base weights assigned successfully in {end_time - start_time:.2f} seconds.", flush=True)
+    logging.info(f"[INFO] Base weights assigned successfully in {end_time - start_time:.2f} seconds.")
+    return df
+
+def prepare_dataset(file):
+    print("[INFO] Starting dataset preparation...")
+    start_time = time.time()
+    df = load_data(file)
+    if df is None:
+        raise ValueError("Failed to load data.")
+    if not {"repo", "parent"}.issubset(df.columns):
+        raise ValueError("Input CSV must contain 'repo' and 'parent' columns.")
+    print("[INFO] Fetching GitHub features...")
+    df = fetch_github_features(df)
+    print("[INFO] GitHub features fetched successfully.")
+    print("[INFO] Assigning base weights using LLama model...")
+    df = assign_base_weight(df)
+    end_time = time.time()
+    print(f"[INFO] Dataset preparation completed in {end_time - start_time:.2f} seconds.")
+    return df
+
+
+##############################
+# Enhanced RandomForest Regression
+##############################
+def train_predict_weight(df):
+    print("[INFO] Starting weight prediction...", flush=True)
+    start_time = time.time()
+    target = "base_weight"
+    feature_cols = ["stars", "forks", "watchers", "open_issues", "pulls", "activity", "contributors"]
+    if target not in df.columns:
+        raise ValueError("Base weight column missing.")
+    X = df[feature_cols]
+    y = df[target]
+    print("[INFO] Splitting data into training and testing sets...", flush=True)
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    rf_model = RandomForestRegressor(random_state=42)
+    param_grid = {
+        "n_estimators": [100, 200, 300],
+        "max_depth": [None, 10, 20, 30],
+        "min_samples_split": [2, 5, 10],
+        "min_samples_leaf": [1, 2, 4]
+    }
+    print("[INFO] Performing grid search for hyperparameter tuning...", flush=True)
+    gridSearch = GridSearchCV(
+        estimator=rf_model,
+        param_grid=param_grid,
+        cv=5,
+        scoring="neg_mean_squared_error"
+    )
+    gridSearch.fit(X_train, y_train)
+    print("[INFO] Grid search completed.", flush=True)
+    print("Best Parameters:", gridSearch.best_params_, flush=True)
+    print("Best MSE:", -gridSearch.best_score_, flush=True)
+    y_pred = gridSearch.best_estimator_.predict(X_test)
+    mse = mean_squared_error(y_test, y_pred)
+    print("Final RF Test MSE:", mse, flush=True)
+    print("[INFO] Predicting final weights for all rows...")
+    df["final_weight"] = gridSearch.best_estimator_.predict(X)
+    end_time = time.time()
+    print(f"[INFO] Weight prediction completed in {end_time - start_time:.2f} seconds.", flush=True)
+    return df
+
+##############################
+# CSV Output
+##############################
+def create_submission_csv(df, output_filename="submission.csv"):
+    print(f"[INFO] Writing results to {output_filename}...", flush=True)
+    required_cols = ["repo", "parent", "final_weight"]
+    submission_df = df[required_cols]
+    submission_df.to_csv(output_filename, index=False)
+    print(f"[INFO] Results written to {output_filename}.", flush=True)
+    return output_filename
+
+# Removed Gradio UI code from this file to ensure modular workflow.
+# This file now focuses solely on data processing and prediction.
+
+if __name__ == "__main__":
+    print("DeepFunding Oracle is now ready for backend processing.", flush=True)

README.md

@@ -1,13 +1,3 @@
 ---
-title: DeepFundingOracle
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
-sdk: gradio
-sdk_version: 5.0.1
-app_file: app.py
-pinned: false
-short_description: 'Oracle for predicting funding for projects '
+license: llama3
 ---
-
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

app.py

@@ -1,64 +1,27 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+from Oracle.deepfundingoracle import prepare_dataset, train_predict_weight, create_submission_csv
+
+# Gradio-only deployment entrypoint for Hugging Face Spaces
+def analyze_file(upload):
+    # upload is a file-like object with .name
+    df = prepare_dataset(upload.name)
+    df = train_predict_weight(df)
+    csv_path = create_submission_csv(df, "submission.csv")
+    preview = df.head().to_csv(index=False)
+    return preview, csv_path
+
+iface = gr.Interface(
+    fn=analyze_file,
+    inputs=gr.File(label="Upload CSV", type="file"),
+    outputs=[
+        gr.Textbox(label="Preview of Results"),
+        gr.Textbox(label="Download CSV Path")
     ],
+    title="DeepFunding Oracle",
+    description="Upload a CSV of repo-parent relationships; returns base and final weight predictions as CSV."
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    port = int(os.environ.get("PORT", 7860))
+    iface.launch(server_name="0.0.0.0", server_port=port)

data/test2.csv

@@ -0,0 +1,100 @@
+repo,parent
+https://github.com/web3/web3.js,ethereum
+https://github.com/prysmaticlabs/prysm,ethereum
+https://github.com/ethereum/fe,ethereum
+https://github.com/ethereum/remix-project,ethereum
+https://github.com/eth-infinitism/account-abstraction,ethereum
+https://github.com/wevm/viem,ethereum
+https://github.com/nethereum/nethereum,ethereum
+https://github.com/ethers-io/ethers.js,ethereum
+https://github.com/chainsafe/lodestar,ethereum
+https://github.com/ethereum-lists/chains,ethereum
+https://github.com/sigp/lighthouse,ethereum
+https://github.com/ethereum/py-evm,ethereum
+https://github.com/hyperledger/besu,ethereum
+https://github.com/erigontech/erigon,ethereum
+https://github.com/vyperlang/titanoboa,ethereum
+https://github.com/alloy-rs/alloy,ethereum
+https://github.com/ethereumjs/ethereumjs-monorepo,ethereum
+https://github.com/foundry-rs/foundry,ethereum
+https://github.com/safe-global/safe-smart-account,ethereum
+https://github.com/consensys/teku,ethereum
+https://github.com/grandinetech/grandine,ethereum
+https://github.com/ethereum/sourcify,ethereum
+https://github.com/ethereum/solidity,ethereum
+https://github.com/status-im/nimbus-eth2,ethereum
+https://github.com/openzeppelin/openzeppelin-contracts,ethereum
+https://github.com/ethereum/web3.py,ethereum
+https://github.com/nethermindeth/nethermind,ethereum
+https://github.com/apeworx/ape,ethereum
+https://github.com/a16z/helios,ethereum
+https://github.com/paradigmxyz/reth,ethereum
+https://github.com/scaffold-eth/scaffold-eth-2,ethereum
+https://github.com/vyperlang/vyper,ethereum
+https://github.com/hyperledger-web3j/web3j,ethereum
+https://github.com/ethereum/go-ethereum,ethereum
+https://github.com/nomicfoundation/hardhat,ethereum
+https://github.com/census-instrumentation/opencensus-go,https://github.com/prysmaticlabs/prysm
+https://github.com/pion/turn,https://github.com/prysmaticlabs/prysm
+https://github.com/google/pprof,https://github.com/prysmaticlabs/prysm
+https://github.com/uber-go/fx,https://github.com/prysmaticlabs/prysm
+https://github.com/elastic/gosigar,https://github.com/prysmaticlabs/prysm
+https://github.com/cockroachdb/logtags,https://github.com/prysmaticlabs/prysm
+https://github.com/tklauser/go-sysconf,https://github.com/prysmaticlabs/prysm
+https://github.com/manifoldco/promptui,https://github.com/prysmaticlabs/prysm
+https://github.com/cockroachdb/errors,https://github.com/prysmaticlabs/prysm
+https://github.com/coreos/go-systemd,https://github.com/prysmaticlabs/prysm
+https://github.com/herumi/bls-eth-go-binary,https://github.com/prysmaticlabs/prysm
+https://github.com/spf13/afero,https://github.com/prysmaticlabs/prysm
+https://github.com/gorilla/websocket,https://github.com/prysmaticlabs/prysm
+https://github.com/libp2p/go-reuseport,https://github.com/prysmaticlabs/prysm
+https://github.com/hashicorp/golang-lru,https://github.com/prysmaticlabs/prysm
+https://github.com/ianlancetaylor/cgosymbolizer,https://github.com/prysmaticlabs/prysm
+https://github.com/huin/goupnp,https://github.com/prysmaticlabs/prysm
+https://github.com/olekukonko/tablewriter,https://github.com/prysmaticlabs/prysm
+https://github.com/pion/webrtc,https://github.com/prysmaticlabs/prysm
+https://github.com/d4l3k/messagediff,https://github.com/prysmaticlabs/prysm
+https://github.com/decred/dcrd,https://github.com/prysmaticlabs/prysm
+https://github.com/multiformats/go-multihash,https://github.com/prysmaticlabs/prysm
+https://github.com/kubernetes/klog,https://github.com/prysmaticlabs/prysm
+https://github.com/flynn/noise,https://github.com/prysmaticlabs/prysm
+https://github.com/mikioh/tcpinfo,https://github.com/prysmaticlabs/prysm
+https://github.com/json-iterator/go,https://github.com/prysmaticlabs/prysm
+https://github.com/pion/logging,https://github.com/prysmaticlabs/prysm
+https://github.com/btcsuite/btcd,https://github.com/prysmaticlabs/prysm
+https://github.com/mgutz/ansi,https://github.com/prysmaticlabs/prysm
+https://github.com/mattn/go-runewidth,https://github.com/prysmaticlabs/prysm
+https://github.com/munnerz/goautoneg,https://github.com/prysmaticlabs/prysm
+https://github.com/lukechampine/blake3,https://github.com/prysmaticlabs/prysm
+https://github.com/wealdtech/go-eth2-wallet-encryptor-keystorev4,https://github.com/prysmaticlabs/prysm
+https://github.com/libp2p/go-msgio,https://github.com/prysmaticlabs/prysm
+https://github.com/pion/transport,https://github.com/prysmaticlabs/prysm
+https://github.com/minio/highwayhash,https://github.com/prysmaticlabs/prysm
+https://github.com/kubernetes-sigs/structured-merge-diff,https://github.com/prysmaticlabs/prysm
+https://github.com/bits-and-blooms/bitset,https://github.com/prysmaticlabs/prysm
+https://github.com/libp2p/go-buffer-pool,https://github.com/prysmaticlabs/prysm
+https://github.com/holiman/uint256,https://github.com/prysmaticlabs/prysm
+https://github.com/holiman/billy,https://github.com/prysmaticlabs/prysm
+https://github.com/chzyer/readline,https://github.com/prysmaticlabs/prysm
+https://github.com/grpc-ecosystem/go-grpc-middleware,https://github.com/prysmaticlabs/prysm
+https://github.com/consensys/gnark-crypto,https://github.com/prysmaticlabs/prysm
+https://github.com/kubernetes-sigs/json,https://github.com/prysmaticlabs/prysm
+https://github.com/influxdata/influxdb-client-go,https://github.com/prysmaticlabs/prysm
+https://github.com/ethereum/go-verkle,https://github.com/prysmaticlabs/prysm
+https://github.com/quic-go/quic-go,https://github.com/prysmaticlabs/prysm
+https://github.com/k0kubun/go-ansi,https://github.com/prysmaticlabs/prysm
+https://github.com/go-yaml/yaml,https://github.com/prysmaticlabs/prysm
+https://github.com/raulk/go-watchdog,https://github.com/prysmaticlabs/prysm
+https://github.com/godbus/dbus,https://github.com/prysmaticlabs/prysm
+https://github.com/grpc/grpc-go,https://github.com/prysmaticlabs/prysm
+https://github.com/mattn/go-isatty,https://github.com/prysmaticlabs/prysm
+https://github.com/nxadm/tail,https://github.com/prysmaticlabs/prysm
+https://github.com/tyler-smith/go-bip39,https://github.com/prysmaticlabs/prysm
+https://github.com/docker/go-units,https://github.com/prysmaticlabs/prysm
+https://github.com/wlynxg/anet,https://github.com/prysmaticlabs/prysm
+https://github.com/uber-go/dig,https://github.com/prysmaticlabs/prysm
+https://github.com/kubernetes/client-go,https://github.com/prysmaticlabs/prysm
+https://github.com/libp2p/go-flow-metrics,https://github.com/prysmaticlabs/prysm
+https://github.com/mmcloughlin/addchain,https://github.com/prysmaticlabs/prysm
+https://github.com/mohae/deepcopy,https://github.com/prysmaticlabs/prysm
+https://github.com/multiformats/go-base36,https://github.com/prysmaticlabs/prysm

deepfundingoracle.log

@@ -0,0 +1,3 @@
+2025-04-19 14:13:36,946 - INFO - [INFO] Assigning base weights using LLama model...
+2025-04-19 14:22:31,541 - INFO - [INFO] Assigning base weights using LLama model...
+2025-04-19 14:31:26,535 - INFO - [INFO] Assigning base weights using LLama model...

requirements.txt

@@ -1 +1,11 @@
-huggingface_hub==0.25.2
+polars
+pandas
+scikit-learn
+lightgbm
+altair
+transformers
+smolagents
+huggingface_hub
+gradio
+fastapi
+uvicorn[standard]