Release 0.1.7 (#93)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

CHANGELOG.md

@@ -1,5 +1,15 @@
 # create-llama
 
+## 0.1.7
+
+### Patch Changes
+
+- 260d37a: Add system prompt env variable for TS
+- bbd5b8d: Fix postgres connection leaking issue
+- bb53425: Support HTTP proxies by setting the GLOBAL_AGENT_HTTP_PROXY env variable
+- 69c2e16: Fix streaming for Express
+- 7873bfb: Update Ollama provider to run with the base URL from the environment variable
+
 ## 0.1.6
 
 ### Patch Changes

helpers/env-variables.ts

@@ -219,6 +219,15 @@ const getModelEnvs = (modelConfig: ModelConfig): EnvVar[] => {
           },
         ]
       : []),
+    ...(modelConfig.provider === "ollama"
+      ? [
+          {
+            name: "OLLAMA_BASE_URL",
+            description:
+              "The base URL for the Ollama API. Eg: http://127.0.0.1:11434",
+          },
+        ]
+      : []),
   ];
 };
 
@@ -240,13 +249,6 @@ const getFrameworkEnvs = (
       description: "The port to start the backend app.",
       value: port?.toString() || "8000",
     },
-    // TODO: Once LlamaIndexTS supports string templates, move this to `getEngineEnvs`
-    {
-      name: "SYSTEM_PROMPT",
-      description: `Custom system prompt.
-Example:
-SYSTEM_PROMPT="You are a helpful assistant who helps users with their questions."`,
-    },
   ];
 };
 
@@ -258,6 +260,12 @@ const getEngineEnvs = (): EnvVar[] => {
         "The number of similar embeddings to return when retrieving documents.",
       value: "3",
     },
+    {
+      name: "SYSTEM_PROMPT",
+      description: `Custom system prompt.
+Example:
+SYSTEM_PROMPT="You are a helpful assistant who helps users with their questions."`,
+    },
   ];
 };
 

helpers/proxy.ts

@@ -0,0 +1,8 @@
+/* Function to conditionally load the global-agent/bootstrap module */
+export async function initializeGlobalAgent() {
+  if (process.env.GLOBAL_AGENT_HTTP_PROXY) {
+    /* Dynamically import global-agent/bootstrap */
+    await import("global-agent/bootstrap");
+    console.log("Proxy enabled via global-agent.");
+  }
+}

index.ts

@@ -12,12 +12,16 @@ import { createApp } from "./create-app";
 import { getDataSources } from "./helpers/datasources";
 import { getPkgManager } from "./helpers/get-pkg-manager";
 import { isFolderEmpty } from "./helpers/is-folder-empty";
+import { initializeGlobalAgent } from "./helpers/proxy";
 import { runApp } from "./helpers/run-app";
 import { getTools } from "./helpers/tools";
 import { validateNpmName } from "./helpers/validate-pkg";
 import packageJson from "./package.json";
 import { QuestionArgs, askQuestions, onPromptState } from "./questions";
 
+// Run the initialization function
+initializeGlobalAgent();
+
 let projectPath: string = "";
 
 const handleSigTerm = () => process.exit(0);

package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-llama",
-  "version": "0.1.6",
+  "version": "0.1.7",
   "description": "Create LlamaIndex-powered apps with one command",
   "keywords": [
     "rag",
@@ -52,6 +52,7 @@
     "cross-spawn": "7.0.3",
     "fast-glob": "3.3.1",
     "fs-extra": "11.2.0",
+    "global-agent": "^3.0.0",
     "got": "10.7.0",
     "ollama": "^0.5.0",
     "ora": "^8.0.1",

templates/components/engines/typescript/agent/chat.ts

@@ -41,5 +41,6 @@ export async function createChatEngine() {
 
   return new OpenAIAgent({
     tools,
+    systemPrompt: process.env.SYSTEM_PROMPT,
   });
 }

templates/components/engines/typescript/chat/chat.ts

@@ -16,5 +16,6 @@ export async function createChatEngine() {
   return new ContextChatEngine({
     chatModel: Settings.llm,
     retriever,
+    systemPrompt: process.env.SYSTEM_PROMPT,
   });
 }

templates/components/vectordbs/python/none/index.py

@@ -1,12 +1,22 @@
-import logging
 import os
+import logging
+from datetime import timedelta
 
+from cachetools import cached, TTLCache
 from llama_index.core.storage import StorageContext
 from llama_index.core.indices import load_index_from_storage
 
 logger = logging.getLogger("uvicorn")
 
 
+@cached(
+    TTLCache(maxsize=10, ttl=timedelta(minutes=5).total_seconds()),
+    key=lambda *args, **kwargs: "global_storage_context",
+)
+def get_storage_context(persist_dir: str) -> StorageContext:
+    return StorageContext.from_defaults(persist_dir=persist_dir)
+
+
 def get_index():
     storage_dir = os.getenv("STORAGE_DIR", "storage")
     # check if storage already exists
@@ -14,7 +24,7 @@ def get_index():
         return None
     # load the existing index
     logger.info(f"Loading index from {storage_dir}...")
-    storage_context = StorageContext.from_defaults(persist_dir=storage_dir)
+    storage_context = get_storage_context(storage_dir)
     index = load_index_from_storage(storage_context)
     logger.info(f"Finished loading index from {storage_dir}")
     return index

templates/components/vectordbs/python/pg/vectordb.py

@@ -5,26 +5,33 @@ from urllib.parse import urlparse
 PGVECTOR_SCHEMA = "public"
 PGVECTOR_TABLE = "llamaindex_embedding"
 
+vector_store: PGVectorStore = None
+
 
 def get_vector_store():
-    original_conn_string = os.environ.get("PG_CONNECTION_STRING")
-    if original_conn_string is None or original_conn_string == "":
-        raise ValueError("PG_CONNECTION_STRING environment variable is not set.")
+    global vector_store
 
-    # The PGVectorStore requires both two connection strings, one for psycopg2 and one for asyncpg
-    # Update the configured scheme with the psycopg2 and asyncpg schemes
-    original_scheme = urlparse(original_conn_string).scheme + "://"
-    conn_string = original_conn_string.replace(
-        original_scheme, "postgresql+psycopg2://"
-    )
-    async_conn_string = original_conn_string.replace(
-        original_scheme, "postgresql+asyncpg://"
-    )
+    if vector_store is None:
+        original_conn_string = os.environ.get("PG_CONNECTION_STRING")
+        if original_conn_string is None or original_conn_string == "":
+            raise ValueError("PG_CONNECTION_STRING environment variable is not set.")
 
-    return PGVectorStore(
-        connection_string=conn_string,
-        async_connection_string=async_conn_string,
-        schema_name=PGVECTOR_SCHEMA,
-        table_name=PGVECTOR_TABLE,
-        embed_dim=int(os.environ.get("EMBEDDING_DIM", 1024)),
-    )
+        # The PGVectorStore requires both two connection strings, one for psycopg2 and one for asyncpg
+        # Update the configured scheme with the psycopg2 and asyncpg schemes
+        original_scheme = urlparse(original_conn_string).scheme + "://"
+        conn_string = original_conn_string.replace(
+            original_scheme, "postgresql+psycopg2://"
+        )
+        async_conn_string = original_conn_string.replace(
+            original_scheme, "postgresql+asyncpg://"
+        )
+
+        vector_store = PGVectorStore(
+            connection_string=conn_string,
+            async_connection_string=async_conn_string,
+            schema_name=PGVECTOR_SCHEMA,
+            table_name=PGVECTOR_TABLE,
+            embed_dim=int(os.environ.get("EMBEDDING_DIM", 1024)),
+        )
+
+    return vector_store

templates/types/streaming/express/package.json

@@ -14,7 +14,7 @@
     "cors": "^2.8.5",
     "dotenv": "^16.3.1",
     "express": "^4.18.2",
-    "llamaindex": "0.3.9",
+    "llamaindex": "0.3.13",
     "pdf2json": "3.0.5",
     "ajv": "^8.12.0"
   },

templates/types/streaming/express/src/controllers/chat.controller.ts

@@ -64,9 +64,8 @@ export const chat = async (req: Request, res: Response) => {
         image_url: data?.imageUrl,
       },
     });
-    const processedStream = stream.pipeThrough(vercelStreamData.stream);
 
-    return streamToResponse(processedStream, res);
+    return streamToResponse(stream, res, {}, vercelStreamData);
   } catch (error) {
     console.error("[LlamaIndex]", error);
     return res.status(500).json({

templates/types/streaming/express/src/controllers/engine/settings.ts

@@ -56,11 +56,17 @@ function initOpenAI() {
 }
 
 function initOllama() {
+  const config = {
+    host: process.env.OLLAMA_BASE_URL ?? "http://127.0.0.1:11434",
+  };
+
   Settings.llm = new Ollama({
     model: process.env.MODEL ?? "",
+    config,
   });
   Settings.embedModel = new OllamaEmbedding({
     model: process.env.EMBEDDING_MODEL ?? "",
+    config,
   });
 }
 

templates/types/streaming/fastapi/app/settings.py

@@ -23,8 +23,12 @@ def init_ollama():
     from llama_index.llms.ollama import Ollama
     from llama_index.embeddings.ollama import OllamaEmbedding
 
-    Settings.embed_model = OllamaEmbedding(model_name=os.getenv("EMBEDDING_MODEL"))
-    Settings.llm = Ollama(model=os.getenv("MODEL"))
+    base_url = os.getenv("OLLAMA_BASE_URL") or "http://127.0.0.1:11434"
+    Settings.embed_model = OllamaEmbedding(
+        base_url=base_url,
+        model_name=os.getenv("EMBEDDING_MODEL"),
+    )
+    Settings.llm = Ollama(base_url=base_url, model=os.getenv("MODEL"))
 
 
 def init_openai():

templates/types/streaming/fastapi/pyproject.toml

@@ -16,6 +16,7 @@ python-dotenv = "^1.0.0"
 aiostream = "^0.5.2"
 llama-index = "0.10.28"
 llama-index-core = "0.10.28"
+cachetools = "^5.3.3"
 
 [build-system]
 requires = ["poetry-core"]

templates/types/streaming/nextjs/app/api/chat/engine/settings.ts

@@ -56,11 +56,16 @@ function initOpenAI() {
 }
 
 function initOllama() {
+  const config = {
+    host: process.env.OLLAMA_BASE_URL ?? "http://127.0.0.1:11434",
+  };
   Settings.llm = new Ollama({
     model: process.env.MODEL ?? "",
+    config,
   });
   Settings.embedModel = new OllamaEmbedding({
     model: process.env.EMBEDDING_MODEL ?? "",
+    config,
   });
 }
 

templates/types/streaming/nextjs/package.json

@@ -18,7 +18,7 @@
     "class-variance-authority": "^0.7.0",
     "clsx": "^2.1.1",
     "dotenv": "^16.3.1",
-    "llamaindex": "0.3.8",
+    "llamaindex": "0.3.13",
     "lucide-react": "^0.294.0",
     "next": "^14.0.3",
     "pdf2json": "3.0.5",

tsconfig.json

@@ -11,14 +11,16 @@
     "forceConsistentCasingInFileNames": true,
     "incremental": true,
     "outDir": "./lib",
-    "tsBuildInfoFile": "./lib/.tsbuildinfo"
+    "tsBuildInfoFile": "./lib/.tsbuildinfo",
+    "typeRoots": ["./types", "./node_modules/@types"]
   },
   "include": [
     "create-app.ts",
     "index.ts",
     "./helpers",
     "questions.ts",
-    "package.json"
+    "package.json",
+    "types/**/*"
   ],
   "exclude": ["dist"]
 }

types/global-agent.d.ts

@@ -0,0 +1 @@
+declare module "global-agent/bootstrap";