Merge branch 'main' into feat/implement-csv-upload

Author: thucpn

.changeset/itchy-ads-travel.md

@@ -0,0 +1,5 @@
+---
+"create-llama": patch
+---
+
+Add support E2B code interpreter tool for FastAPI

helpers/index.ts

@@ -171,6 +171,11 @@ export const installTemplate = async (
         );
       }
     }
+
+    // Create tool-output directory
+    if (props.tools && props.tools.length > 0) {
+      await fsExtra.mkdir(path.join(props.root, "tool-output"));
+    }
   } else {
     // this is a frontend for a full-stack app, create .env file with model information
     await createFrontendEnvFile(props.root, {

helpers/tools.ts

@@ -90,8 +90,13 @@ export const supportedTools: Tool[] = [
   {
     display: "Code Interpreter",
     name: "interpreter",
-    dependencies: [],
-    supportedFrameworks: ["express", "nextjs"],
+    dependencies: [
+      {
+        name: "e2b_code_interpreter",
+        version: "0.0.7",
+      },
+    ],
+    supportedFrameworks: ["fastapi", "express", "nextjs"],
     type: ToolType.LOCAL,
     envVars: [
       {
@@ -154,7 +159,6 @@ export const writeToolsConfig = async (
   tools: Tool[] = [],
   type: ConfigFileType = ConfigFileType.YAML,
 ) => {
-  if (tools.length === 0) return; // no tools selected, no config need
   const configContent: {
     [key in ToolType]: Record<string, any>;
   } = {

templates/components/engines/python/agent/tools/interpreter.py

@@ -0,0 +1,134 @@
+import os
+import logging
+import base64
+import uuid
+from pydantic import BaseModel
+from typing import List, Tuple, Dict
+from llama_index.core.tools import FunctionTool
+from e2b_code_interpreter import CodeInterpreter
+from e2b_code_interpreter.models import Logs
+
+
+logger = logging.getLogger(__name__)
+
+
+class InterpreterExtraResult(BaseModel):
+    type: str
+    filename: str
+    url: str
+
+
+class E2BToolOutput(BaseModel):
+    is_error: bool
+    logs: Logs
+    results: List[InterpreterExtraResult] = []
+
+
+class E2BCodeInterpreter:
+
+    output_dir = "tool-output"
+
+    def __init__(self, api_key: str, filesever_url_prefix: str):
+        self.api_key = api_key
+        self.filesever_url_prefix = filesever_url_prefix
+
+    def get_output_path(self, filename: str) -> str:
+        # if output directory doesn't exist, create it
+        if not os.path.exists(self.output_dir):
+            os.makedirs(self.output_dir, exist_ok=True)
+        return os.path.join(self.output_dir, filename)
+
+    def save_to_disk(self, base64_data: str, ext: str) -> Dict:
+        filename = f"{uuid.uuid4()}.{ext}"  # generate a unique filename
+        buffer = base64.b64decode(base64_data)
+        output_path = self.get_output_path(filename)
+
+        try:
+            with open(output_path, "wb") as file:
+                file.write(buffer)
+        except IOError as e:
+            logger.error(f"Failed to write to file {output_path}: {str(e)}")
+            raise e
+
+        logger.info(f"Saved file to {output_path}")
+
+        return {
+            "outputPath": output_path,
+            "filename": filename,
+        }
+
+    def get_file_url(self, filename: str) -> str:
+        return f"{self.filesever_url_prefix}/{self.output_dir}/{filename}"
+
+    def parse_result(self, result) -> List[InterpreterExtraResult]:
+        """
+        The result could include multiple formats (e.g. png, svg, etc.) but encoded in base64
+        We save each result to disk and return saved file metadata (extension, filename, url)
+        """
+        if not result:
+            return []
+
+        output = []
+
+        try:
+            formats = result.formats()
+            base64_data_arr = [result[format] for format in formats]
+
+            for ext, base64_data in zip(formats, base64_data_arr):
+                if ext and base64_data:
+                    result = self.save_to_disk(base64_data, ext)
+                    filename = result["filename"]
+                    output.append(
+                        InterpreterExtraResult(
+                            type=ext, filename=filename, url=self.get_file_url(filename)
+                        )
+                    )
+        except Exception as error:
+            logger.error("Error when saving data to disk", error)
+
+        return output
+
+    def interpret(self, code: str) -> E2BToolOutput:
+        with CodeInterpreter(api_key=self.api_key) as interpreter:
+            logger.info(
+                f"\n{'='*50}\n> Running following AI-generated code:\n{code}\n{'='*50}"
+            )
+            exec = interpreter.notebook.exec_cell(code)
+
+            if exec.error:
+                output = E2BToolOutput(is_error=True, logs=[exec.error])
+            else:
+                if len(exec.results) == 0:
+                    output = E2BToolOutput(is_error=False, logs=exec.logs, results=[])
+                else:
+                    results = self.parse_result(exec.results[0])
+                    output = E2BToolOutput(
+                        is_error=False, logs=exec.logs, results=results
+                    )
+            return output
+
+
+def code_interpret(code: str) -> Dict:
+    """
+    Execute python code in a Jupyter notebook cell and return any result, stdout, stderr, display_data, and error.
+    """
+    api_key = os.getenv("E2B_API_KEY")
+    filesever_url_prefix = os.getenv("FILESERVER_URL_PREFIX")
+    if not api_key:
+        raise ValueError(
+            "E2B_API_KEY key is required to run code interpreter. Get it here: https://e2b.dev/docs/getting-started/api-key"
+        )
+    if not filesever_url_prefix:
+        raise ValueError(
+            "FILESERVER_URL_PREFIX is required to display file output from sandbox"
+        )
+
+    interpreter = E2BCodeInterpreter(
+        api_key=api_key, filesever_url_prefix=filesever_url_prefix
+    )
+    output = interpreter.interpret(code)
+    return output.dict()
+
+
+# Specify as functions tools to be loaded by the ToolFactory
+tools = [FunctionTool.from_defaults(code_interpret)]

templates/components/engines/typescript/agent/tools/interpreter.ts

@@ -15,7 +15,7 @@ export type InterpreterToolParams = {
   fileServerURLPrefix?: string;
 };
 
-export type InterpreterToolOuput = {
+export type InterpreterToolOutput = {
   isError: boolean;
   logs: Logs;
   extraResult: InterpreterExtraResult[];
@@ -88,23 +88,23 @@ export class InterpreterTool implements BaseTool<InterpreterParameter> {
     return this.codeInterpreter;
   }
 
-  public async codeInterpret(code: string): Promise<InterpreterToolOuput> {
+  public async codeInterpret(code: string): Promise<InterpreterToolOutput> {
     console.log(
       `\n${"=".repeat(50)}\n> Running following AI-generated code:\n${code}\n${"=".repeat(50)}`,
     );
     const interpreter = await this.initInterpreter();
     const exec = await interpreter.notebook.execCell(code);
     if (exec.error) console.error("[Code Interpreter error]", exec.error);
     const extraResult = await this.getExtraResult(exec.results[0]);
-    const result: InterpreterToolOuput = {
+    const result: InterpreterToolOutput = {
       isError: !!exec.error,
       logs: exec.logs,
       extraResult,
     };
     return result;
   }
 
-  async call(input: InterpreterParameter): Promise<InterpreterToolOuput> {
+  async call(input: InterpreterParameter): Promise<InterpreterToolOutput> {
     const result = await this.codeInterpret(input.code);
     await this.codeInterpreter?.close();
     return result;

templates/types/streaming/express/src/controllers/stream-helper.ts

@@ -43,6 +43,7 @@ export function appendSourceData(
         ...node.node.toMutableJSON(),
         id: node.node.id_,
         score: node.score ?? null,
+        url: getNodeUrl(node.node.metadata),
       })),
     },
   });

templates/types/streaming/fastapi/app/api/routers/chat.py

@@ -1,3 +1,5 @@
+import os
+import logging
 from pydantic import BaseModel
 from typing import List, Any, Optional, Dict, Tuple
 from fastapi import APIRouter, Depends, HTTPException, Request, status
@@ -11,6 +13,7 @@
 
 chat_router = r = APIRouter()
 
+logger = logging.getLogger("uvicorn")
 
 class _Message(BaseModel):
     role: MessageRole
@@ -38,14 +41,27 @@ class _SourceNodes(BaseModel):
     metadata: Dict[str, Any]
     score: Optional[float]
     text: str
+    url: Optional[str]
 
     @classmethod
     def from_source_node(cls, source_node: NodeWithScore):
+        metadata = source_node.node.metadata
+        url = metadata.get("URL")
+        
+        if not url:
+            file_name = metadata.get("file_name")
+            url_prefix = os.getenv("FILESERVER_URL_PREFIX")
+            if not url_prefix:
+                logger.warning("Warning: FILESERVER_URL_PREFIX not set in environment variables")
+            if file_name and url_prefix:
+                url = f"{url_prefix}/data/{file_name}"
+
         return cls(
             id=source_node.node.node_id,
-            metadata=source_node.node.metadata,
+            metadata=metadata,
             score=source_node.score,
             text=source_node.node.text,  # type: ignore
+            url=url
         )
 
     @classmethod
@@ -93,7 +109,13 @@ async def chat(
 
     event_handler = EventCallbackHandler()
     chat_engine.callback_manager.handlers.append(event_handler)  # type: ignore
-    response = await chat_engine.astream_chat(last_message_content, messages)
+    try:
+        response = await chat_engine.astream_chat(last_message_content, messages)
+    except Exception as e:
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=f"Error in chat engine: {e}",
+        )
 
     async def content_generator():
         # Yield the text response

templates/types/streaming/fastapi/app/api/routers/messaging.py

@@ -1,12 +1,16 @@
 import json
 import asyncio
+import logging
 from typing import AsyncGenerator, Dict, Any, List, Optional
 from llama_index.core.callbacks.base import BaseCallbackHandler
 from llama_index.core.callbacks.schema import CBEventType
 from llama_index.core.tools.types import ToolOutput
 from pydantic import BaseModel
 
 
+logger = logging.getLogger(__name__)
+
+
 class CallbackEvent(BaseModel):
     event_type: CBEventType
     payload: Optional[Dict[str, Any]] = None
@@ -72,15 +76,19 @@ def get_agent_tool_response(self) -> dict | None:
                     }
 
     def to_response(self):
-        match self.event_type:
-            case "retrieve":
-                return self.get_retrieval_message()
-            case "function_call":
-                return self.get_tool_message()
-            case "agent_step":
-                return self.get_agent_tool_response()
-            case _:
-                return None
+        try:
+            match self.event_type:
+                case "retrieve":
+                    return self.get_retrieval_message()
+                case "function_call":
+                    return self.get_tool_message()
+                case "agent_step":
+                    return self.get_agent_tool_response()
+                case _:
+                    return None
+        except Exception as e:
+            logger.error(f"Error in converting event to response: {e}")
+            return None
 
 
 class EventCallbackHandler(BaseCallbackHandler):

templates/types/streaming/fastapi/main.py

@@ -37,8 +37,17 @@
     async def redirect_to_docs():
         return RedirectResponse(url="/docs")
 
-if os.path.exists("data"):
-    app.mount("/api/files/data", StaticFiles(directory="data"), name="data-static")
+
+def mount_static_files(directory, path):
+    if os.path.exists(directory):
+        app.mount(path, StaticFiles(directory=directory), name=f"{directory}-static")
+
+
+# Mount the data files to serve the file viewer
+mount_static_files("data", "/api/files/data")
+# Mount the output files from tools
+mount_static_files("tool-output", "/api/files/tool-output")
+
 app.include_router(chat_router, prefix="/api/chat")
 
 

templates/types/streaming/nextjs/app/api/chat/stream-helper.ts

@@ -43,6 +43,7 @@ export function appendSourceData(
         ...node.node.toMutableJSON(),
         id: node.node.id_,
         score: node.score ?? null,
+        url: getNodeUrl(node.node.metadata),
       })),
     },
   });