-
+
@@ -408,7 +408,7 @@ All these checks must pass before your PR can be merged.
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
-- [Community Slack 💭](https://join.slack.com/share/enQtOTE0ODczMzk2Nzk4NC01YjUxNjY2YjBlYTFmNDRiZTM3NDFiYTM3MzVkODFiMDVjOGRjMmNmZTZkZTMzOWQzZGQyZWIwYjQ0MWExYmE3)
+- [Community Slack 💭](https://www.litellm.ai/support)
- Our numbers 📞 +1 (770) 8783-106 / +1 (412) 618-6238
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai
diff --git a/certifi-2025.8.3-py3-none-any.whl b/certifi-2025.8.3-py3-none-any.whl
deleted file mode 100644
index b4158ec6717..00000000000
Binary files a/certifi-2025.8.3-py3-none-any.whl and /dev/null differ
diff --git a/charset_normalizer-3.4.3-cp313-cp313-macosx_10_13_universal2.whl b/charset_normalizer-3.4.3-cp313-cp313-macosx_10_13_universal2.whl
deleted file mode 100644
index 659c5408658..00000000000
Binary files a/charset_normalizer-3.4.3-cp313-cp313-macosx_10_13_universal2.whl and /dev/null differ
diff --git a/ci_cd/security_scans.sh b/ci_cd/security_scans.sh
new file mode 100755
index 00000000000..dbf7c657f6f
--- /dev/null
+++ b/ci_cd/security_scans.sh
@@ -0,0 +1,105 @@
+#!/bin/bash
+
+# Security Scans Script for LiteLLM
+# This script runs comprehensive security scans including Trivy and Grype
+
+set -e
+
+echo "Starting security scans for LiteLLM..."
+
+# Function to install Trivy and required tools
+install_trivy() {
+ echo "Installing Trivy and required tools..."
+ sudo apt-get update
+ sudo apt-get install -y wget apt-transport-https gnupg lsb-release jq curl
+ wget -qO - https://aquasecurity.github.io/trivy-repo/deb/public.key | sudo apt-key add -
+ echo "deb https://aquasecurity.github.io/trivy-repo/deb $(lsb_release -sc) main" | sudo tee -a /etc/apt/sources.list.d/trivy.list
+ sudo apt-get update
+ sudo apt-get install trivy
+ echo "Trivy and required tools installed successfully"
+}
+
+# Function to install Grype
+install_grype() {
+ echo "Installing Grype..."
+ curl -sSfL https://raw.githubusercontent.com/anchore/grype/main/install.sh | sudo sh -s -- -b /usr/local/bin
+ echo "Grype installed successfully"
+}
+
+# Function to run Trivy scans
+run_trivy_scans() {
+ echo "Running Trivy scans..."
+
+ echo "Scanning LiteLLM Docs..."
+ trivy fs --scanners vuln --dependency-tree --exit-code 1 --severity HIGH,CRITICAL,MEDIUM ./docs/
+
+ echo "Scanning LiteLLM UI..."
+ trivy fs --scanners vuln --dependency-tree --exit-code 1 --severity HIGH,CRITICAL,MEDIUM ./ui/
+
+ echo "Trivy scans completed successfully"
+}
+
+# Function to build and scan Docker images with Grype
+run_grype_scans() {
+ echo "Running Grype scans..."
+
+ # Temporarily add wheel files to .dockerignore for security scans
+ echo "Temporarily modifying .dockerignore to exclude problematic wheel files..."
+ cp .dockerignore .dockerignore.backup 2>/dev/null || touch .dockerignore.backup
+ echo "/*.whl" >> .dockerignore
+
+ # Build and scan Dockerfile.database
+ echo "Building and scanning Dockerfile.database..."
+ docker build -t litellm-database:latest -f ./docker/Dockerfile.database .
+ grype litellm-database:latest --fail-on critical
+
+ # Build and scan main Dockerfile
+ echo "Building and scanning main Dockerfile..."
+ docker build -t litellm:latest .
+ grype litellm:latest --fail-on critical
+
+ # Restore original .dockerignore
+ echo "Restoring original .dockerignore..."
+ mv .dockerignore.backup .dockerignore
+
+ # Scan the locally built LiteLLM image for vulnerabilities with CVSS >= 4.0
+ echo "Scanning locally built LiteLLM image for high-severity vulnerabilities..."
+ echo "Using locally built image: litellm:latest"
+
+ # Run grype scan and check for vulnerabilities with CVSS >= 4.0
+ echo "Checking for vulnerabilities with CVSS score >= 4.0..."
+ HIGH_SEVERITY_COUNT=$(grype litellm:latest -o json | jq -r '.matches[] | select(.vulnerability.cvss[]?.metrics.baseScore >= 4.0) | .vulnerability.id' | wc -l)
+
+ if [ "$HIGH_SEVERITY_COUNT" -gt 0 ]; then
+ echo "ERROR: Found $HIGH_SEVERITY_COUNT vulnerabilities with CVSS score >= 4.0 in litellm:latest"
+ echo "Detailed vulnerability report:"
+ grype litellm:latest -o json | jq -r '
+ ["Package", "Version", "Vulnerability ID", "CVSS Score", "Severity", "Fix Version", "Description"],
+ (.matches[] | select(.vulnerability.cvss[]?.metrics.baseScore >= 4.0) |
+ [.artifact.name, .artifact.version, .vulnerability.id, .vulnerability.cvss[0].metrics.baseScore, .vulnerability.severity, (.vulnerability.fix.versions[0] // "No fix available"), .vulnerability.description]) |
+ @tsv' | column -t -s $'\t'
+ exit 1
+ else
+ echo "No high-severity vulnerabilities (CVSS >= 4.0) found in litellm:latest"
+ fi
+
+ echo "Grype scans completed successfully"
+}
+
+# Main execution
+main() {
+ echo "Installing security scanning tools..."
+ install_trivy
+ install_grype
+
+ echo "Running filesystem vulnerability scans..."
+ run_trivy_scans
+
+ echo "Running Docker image vulnerability scans..."
+ run_grype_scans
+
+ echo "All security scans completed successfully!"
+}
+
+# Execute main function
+main "$@"
diff --git a/ci_cd/security_scans_readme.md b/ci_cd/security_scans_readme.md
new file mode 100644
index 00000000000..dd64b01c296
--- /dev/null
+++ b/ci_cd/security_scans_readme.md
@@ -0,0 +1,9 @@
+# Security Scans
+
+## Scans that run:
+
+- Trivy scan on `./docs/` (HIGH/CRITICAL/MEDIUM)
+- Trivy scan on `./ui/` (HIGH/CRITICAL/MEDIUM)
+- Grype scan on `Dockerfile.database` (fails on CRITICAL)
+- Grype scan on main `Dockerfile` (fails on CRITICAL)
+- Grype CVSS ≥ 4.0 scan on main `Dockerfile` (fails any vulnerabilities with CVSS ≥ 4.0)
diff --git a/cookbook/litellm_proxy_server/mcp/mcp_with_litellm_proxy.py b/cookbook/litellm_proxy_server/mcp/mcp_with_litellm_proxy.py
new file mode 100644
index 00000000000..351b0920eb8
--- /dev/null
+++ b/cookbook/litellm_proxy_server/mcp/mcp_with_litellm_proxy.py
@@ -0,0 +1,36 @@
+"""
+Use LiteLLM Proxy MCP Gateway to call MCP tools.
+
+When using LiteLLM Proxy, you can use the same MCP tools across all your LLM providers.
+"""
+import openai
+
+client = openai.OpenAI(
+ api_key="sk-1234", # paste your litellm proxy api key here
+ base_url="http://localhost:4000" # paste your litellm proxy base url here
+)
+print("Making API request to Responses API with MCP tools")
+
+response = client.responses.create(
+ model="gpt-5",
+ input=[
+ {
+ "role": "user",
+ "content": "give me TLDR of what BerriAI/litellm repo is about",
+ "type": "message"
+ }
+ ],
+ tools=[
+ {
+ "type": "mcp",
+ "server_label": "litellm",
+ "server_url": "litellm_proxy",
+ "require_approval": "never"
+ }
+ ],
+ stream=True,
+ tool_choice="required"
+)
+
+for chunk in response:
+ print("response chunk: ", chunk)
diff --git a/dist/litellm_ad-1.76.0-py3-none-any.whl b/dist/litellm_ad-1.76.0-py3-none-any.whl
deleted file mode 100644
index 2b0ae2adcd1..00000000000
Binary files a/dist/litellm_ad-1.76.0-py3-none-any.whl and /dev/null differ
diff --git a/dist/litellm_ad-1.76.0.tar.gz b/dist/litellm_ad-1.76.0.tar.gz
deleted file mode 100644
index 19967d5b9f1..00000000000
Binary files a/dist/litellm_ad-1.76.0.tar.gz and /dev/null differ
diff --git a/dist/litellm_ad-1.76.1-py3-none-any.whl b/dist/litellm_ad-1.76.1-py3-none-any.whl
deleted file mode 100644
index ae45000eabe..00000000000
Binary files a/dist/litellm_ad-1.76.1-py3-none-any.whl and /dev/null differ
diff --git a/dist/litellm_ad-1.76.1.tar.gz b/dist/litellm_ad-1.76.1.tar.gz
deleted file mode 100644
index 8afcb9adcda..00000000000
Binary files a/dist/litellm_ad-1.76.1.tar.gz and /dev/null differ
diff --git a/docs/my-website/docs/completion/http_handler_config.md b/docs/my-website/docs/completion/http_handler_config.md
new file mode 100644
index 00000000000..d4a25ce2043
--- /dev/null
+++ b/docs/my-website/docs/completion/http_handler_config.md
@@ -0,0 +1,145 @@
+# Custom HTTP Handler
+
+Configure custom aiohttp sessions for better performance and control in LiteLLM completions.
+
+## Overview
+
+You can now inject custom `aiohttp.ClientSession` instances into LiteLLM for:
+- Custom connection pooling and timeouts
+- Corporate proxy and SSL configurations
+- Performance optimization
+- Request monitoring
+
+## Basic Usage
+
+### Default (No Changes Required)
+```python
+import litellm
+
+# Works exactly as before
+response = await litellm.acompletion(
+ model="gpt-3.5-turbo",
+ messages=[{"role": "user", "content": "Hello!"}]
+)
+```
+
+### Custom Session
+```python
+import aiohttp
+import litellm
+from litellm.llms.custom_httpx.aiohttp_handler import BaseLLMAIOHTTPHandler
+
+# Create optimized session
+session = aiohttp.ClientSession(
+ timeout=aiohttp.ClientTimeout(total=180),
+ connector=aiohttp.TCPConnector(limit=300, limit_per_host=75)
+)
+
+# Replace global handler
+litellm.base_llm_aiohttp_handler = BaseLLMAIOHTTPHandler(client_session=session)
+
+# All completions now use your session
+response = await litellm.acompletion(model="gpt-3.5-turbo", messages=[...])
+```
+
+## Common Patterns
+
+### FastAPI Integration
+```python
+from contextlib import asynccontextmanager
+from fastapi import FastAPI
+import aiohttp
+import litellm
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+ # Startup
+ session = aiohttp.ClientSession(
+ timeout=aiohttp.ClientTimeout(total=180),
+ connector=aiohttp.TCPConnector(limit=300)
+ )
+ litellm.base_llm_aiohttp_handler = BaseLLMAIOHTTPHandler(
+ client_session=session
+ )
+ yield
+ # Shutdown
+ await session.close()
+
+app = FastAPI(lifespan=lifespan)
+
+@app.post("/chat")
+async def chat(messages: list[dict]):
+ return await litellm.acompletion(model="gpt-3.5-turbo", messages=messages)
+```
+
+### Corporate Proxy
+```python
+import ssl
+
+# Custom SSL context
+ssl_context = ssl.create_default_context()
+ssl_context.load_cert_chain('cert.pem', 'key.pem')
+
+# Proxy session
+session = aiohttp.ClientSession(
+ connector=aiohttp.TCPConnector(ssl=ssl_context),
+ trust_env=True # Use environment proxy settings
+)
+
+litellm.base_llm_aiohttp_handler = BaseLLMAIOHTTPHandler(client_session=session)
+```
+
+### High Performance
+```python
+# Optimized for high throughput
+session = aiohttp.ClientSession(
+ timeout=aiohttp.ClientTimeout(total=300),
+ connector=aiohttp.TCPConnector(
+ limit=1000, # High connection limit
+ limit_per_host=200, # Per host limit
+ ttl_dns_cache=600, # DNS cache
+ keepalive_timeout=60, # Keep connections alive
+ enable_cleanup_closed=True
+ )
+)
+
+litellm.base_llm_aiohttp_handler = BaseLLMAIOHTTPHandler(client_session=session)
+```
+
+## Constructor Options
+
+```python
+BaseLLMAIOHTTPHandler(
+ client_session=None, # Custom aiohttp.ClientSession
+ transport=None, # Advanced transport control
+ connector=None, # Custom aiohttp.BaseConnector
+)
+```
+
+## Resource Management
+
+- **User sessions**: You manage the lifecycle (call `await session.close()`)
+- **Auto-created sessions**: Automatically cleaned up by the handler
+- **100% backward compatible**: Existing code works unchanged
+
+## Configuration Tips
+
+### Development
+```python
+session = aiohttp.ClientSession(
+ timeout=aiohttp.ClientTimeout(total=60),
+ connector=aiohttp.TCPConnector(limit=50)
+)
+```
+
+### Production
+```python
+session = aiohttp.ClientSession(
+ timeout=aiohttp.ClientTimeout(total=300),
+ connector=aiohttp.TCPConnector(
+ limit=1000,
+ limit_per_host=200,
+ keepalive_timeout=60
+ )
+)
+```
\ No newline at end of file
diff --git a/docs/my-website/docs/index.md b/docs/my-website/docs/index.md
index d242842c24e..3f5e1b479c3 100644
--- a/docs/my-website/docs/index.md
+++ b/docs/my-website/docs/index.md
@@ -251,7 +251,7 @@ response = completion(
{
"id": "chatcmpl-565d891b-a42e-4c39-8d14-82a1f5208885",
"created": 1734366691,
- "model": "claude-3-sonnet-20240229",
+ "model": "gpt-4o-2024-08-06",
"object": "chat.completion",
"system_fingerprint": null,
"choices": [
diff --git a/docs/my-website/docs/langchain/langchain.md b/docs/my-website/docs/langchain/langchain.md
index 78425a73b99..c67375ce1be 100644
--- a/docs/my-website/docs/langchain/langchain.md
+++ b/docs/my-website/docs/langchain/langchain.md
@@ -162,3 +162,321 @@ Get more details [here](../observability/lunary_integration.md)
## Use LangChain ChatLiteLLM + Langfuse
Checkout this section [here](../observability/langfuse_integration#use-langchain-chatlitellm--langfuse) for more details on how to integrate Langfuse with ChatLiteLLM.
+
+## Using Tags with LangChain and LiteLLM
+
+Tags are a powerful feature in LiteLLM that allow you to categorize, filter, and track your LLM requests. When using LangChain with LiteLLM, you can pass tags through the `extra_body` parameter in the metadata.
+
+### Basic Tag Usage
+
+