Add yaml configuration to remaining llm apps (#7263)

GitOrigin-RevId: 6120038cbad99905bc0867fdb00928c3bd3599e6

Author: szymondudycz

examples/pipelines/adaptive-rag/Dockerfile

@@ -3,9 +3,12 @@ FROM pathwaycom/pathway:latest
 WORKDIR /app
 
 RUN apt-get update \
-    && apt-get install -y python3-opencv \
+    && apt-get install -y python3-opencv tesseract-ocr-eng \
     && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
 
+COPY requirements.txt .
+RUN pip install -U --no-cache-dir -r requirements.txt
+
 COPY . .
 
 EXPOSE 8000

examples/pipelines/adaptive-rag/app.py

@@ -2,71 +2,43 @@
 
 import pathway as pw
 from dotenv import load_dotenv
-from pathway.udfs import DiskCache, ExponentialBackoffRetryStrategy
-from pathway.xpacks.llm import embedders, llms, parsers, splitters
-from pathway.xpacks.llm.question_answering import AdaptiveRAGQuestionAnswerer
-from pathway.xpacks.llm.vector_store import VectorStoreServer
+from pathway.xpacks.llm.question_answering import SummaryQuestionAnswerer
+from pathway.xpacks.llm.servers import QASummaryRestServer
+from pydantic import BaseModel, ConfigDict, InstanceOf
 
 # To use advanced features with Pathway Scale, get your free license key from
 # https://pathway.com/features and paste it below.
 # To use Pathway Community, comment out the line below.
 pw.set_license_key("demo-license-key-with-telemetry")
 
-load_dotenv()
-
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s %(name)s %(levelname)s %(message)s",
     datefmt="%Y-%m-%d %H:%M:%S",
 )
 
+load_dotenv()
 
-if __name__ == "__main__":
-    path = "./data"
-
-    my_folder = pw.io.fs.read(
-        path=path,
-        format="binary",
-        with_metadata=True,
-    )
-
-    sources = [
-        my_folder
-    ]  # define the inputs (local folders, google drive, sharepoint, ...)
-
-    DEFAULT_GPT_MODEL = "gpt-3.5-turbo"
-
-    chat = llms.OpenAIChat(
-        model=DEFAULT_GPT_MODEL,
-        retry_strategy=ExponentialBackoffRetryStrategy(max_retries=6),
-        cache_strategy=DiskCache(),
-        temperature=0.0,
-    )
 
-    app_host = "0.0.0.0"
-    app_port = 8000
+class App(BaseModel):
+    question_answerer: InstanceOf[SummaryQuestionAnswerer]
+    host: str = "0.0.0.0"
+    port: int = 8000
 
-    parser = parsers.ParseUnstructured()
-    text_splitter = splitters.TokenCountSplitter(max_tokens=400)
-    embedder = embedders.OpenAIEmbedder(cache_strategy=DiskCache())
+    with_cache: bool = True
+    terminate_on_error: bool = False
 
-    vector_server = VectorStoreServer(
-        *sources,
-        embedder=embedder,
-        splitter=text_splitter,
-        parser=parser,
-    )
+    def run(self) -> None:
+        server = QASummaryRestServer(self.host, self.port, self.question_answerer)
+        server.run(
+            with_cache=self.with_cache, terminate_on_error=self.terminate_on_error
+        )
 
-    app = AdaptiveRAGQuestionAnswerer(
-        llm=chat,
-        indexer=vector_server,
-        default_llm_name=DEFAULT_GPT_MODEL,
-        n_starting_documents=2,
-        factor=2,
-        max_iterations=4,
-        strict_prompt=True,
-    )
+    model_config = ConfigDict(extra="forbid")
 
-    app.build_server(host=app_host, port=app_port)
 
-    app.run_server(with_cache=True)
+if __name__ == "__main__":
+    with open("app.yaml") as f:
+        config = pw.load_yaml(f)
+    app = App(**config)
+    app.run()

examples/pipelines/adaptive-rag/app.yaml

@@ -0,0 +1,72 @@
+$sources:
+  - !pw.io.fs.read
+    path: data
+    format: binary
+    with_metadata: true
+
+  # - !pw.xpacks.connectors.sharepoint.read 
+  #   url: $SHAREPOINT_URL
+  #   tenant: $SHAREPOINT_TENANT
+  #   client_id: $SHAREPOINT_CLIENT_ID
+  #   cert_path: sharepointcert.pem
+  #   thumbprint: $SHAREPOINT_THUMBPRINT
+  #   root_path: $SHAREPOINT_ROOT
+  #   with_metadata: true
+  #   refresh_interval: 30
+
+  # - !pw.io.gdrive.read
+  #   object_id: $DRIVE_ID
+  #   service_user_credentials_file: gdrive_indexer.json
+  #   name_pattern:
+  #     - "*.pdf"
+  #     - "*.pptx"
+  #   object_size_limit: null
+  #   with_metadata: true
+  #   refresh_interval: 30
+
+$llm: !pw.xpacks.llm.llms.OpenAIChat
+  model: "gpt-3.5-turbo"
+  retry_strategy: !pw.udfs.ExponentialBackoffRetryStrategy
+    max_retries: 6
+  cache_strategy: !pw.udfs.DiskCache
+  temperature: 0.05
+  capacity: 8
+
+$embedder: !pw.xpacks.llm.embedders.OpenAIEmbedder
+  model: "text-embedding-ada-002"
+  cache_strategy: !pw.udfs.DiskCache
+
+$splitter: !pw.xpacks.llm.splitters.TokenCountSplitter
+  max_tokens: 400
+
+$parser: !pw.xpacks.llm.parsers.ParseUnstructured
+
+$retriever_factory: !pw.stdlib.indexing.BruteForceKnnFactory
+  reserved_space: 1000
+  embedder: $embedder
+  metric: !pw.internals.yaml_loader.import_object
+    path: pw.stdlib.indexing.BruteForceKnnMetricKind.COS
+  dimensions: 1536
+  
+
+$document_store: !pw.xpacks.llm.document_store.DocumentStore
+  docs: $sources
+  parser: $parser
+  splitter: $splitter
+  retriever_factory: $retriever_factory
+
+question_answerer: !pw.xpacks.llm.question_answering.AdaptiveRAGQuestionAnswerer
+  llm: $llm
+  indexer: $document_store
+  n_starting_documents: 2
+  factor: 2
+  max_iterations: 4
+  strict_prompt: true
+
+
+# Change host and port by uncommenting these files
+# host: "0.0.0.0"
+# port: 8000
+
+# with_cache: true
+# terminate_on_error: false

examples/pipelines/adaptive-rag/requirements.txt

@@ -0,0 +1 @@
+python-dotenv==1.0.1

examples/pipelines/demo-document-indexing/.env

@@ -3,15 +3,14 @@ FROM pathwaycom/pathway:latest
 WORKDIR /app
 
 RUN apt-get update \
-    && apt-get install -y python3-opencv \
+    && apt-get install -y python3-opencv tesseract-ocr-eng \
     && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
 
 COPY requirements.txt .
-
-RUN pip install --pre -U --no-cache-dir -r requirements.txt
+RUN pip install -U --no-cache-dir -r requirements.txt
 
 COPY . .
 
 EXPOSE 8000
 
-CMD ["python", "main.py"]
+CMD ["python", "app.py"]

examples/pipelines/demo-document-indexing/Dockerfile

@@ -0,0 +1,44 @@
+import logging
+
+import pathway as pw
+from dotenv import load_dotenv
+from pathway.xpacks.llm.document_store import DocumentStore
+from pathway.xpacks.llm.servers import DocumentStoreServer
+from pydantic import BaseModel, ConfigDict, InstanceOf
+
+# To use advanced features with Pathway Scale, get your free license key from
+# https://pathway.com/features and paste it below.
+# To use Pathway Community, comment out the line below.
+pw.set_license_key("demo-license-key-with-telemetry")
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s %(name)s %(levelname)s %(message)s",
+    datefmt="%Y-%m-%d %H:%M:%S",
+)
+
+load_dotenv()
+
+
+class App(BaseModel):
+    document_store: InstanceOf[DocumentStore]
+    host: str = "0.0.0.0"
+    port: int = 8000
+
+    with_cache: bool = True
+    terminate_on_error: bool = False
+
+    def run(self) -> None:
+        server = DocumentStoreServer(self.host, self.port, self.document_store)
+        server.run(
+            with_cache=self.with_cache, terminate_on_error=self.terminate_on_error
+        )
+
+    model_config = ConfigDict(extra="forbid")
+
+
+if __name__ == "__main__":
+    with open("app.yaml") as f:
+        config = pw.load_yaml(f)
+    app = App(**config)
+    app.run()

examples/pipelines/demo-document-indexing/app.py

@@ -0,0 +1,67 @@
+$sources:
+  - !pw.io.fs.read
+    path: files-for-indexing
+    format: binary
+    with_metadata: true
+
+  # - !pw.xpacks.connectors.sharepoint.read 
+  #   url: $SHAREPOINT_URL
+  #   tenant: $SHAREPOINT_TENANT
+  #   client_id: $SHAREPOINT_CLIENT_ID
+  #   cert_path: sharepointcert.pem
+  #   thumbprint: $SHAREPOINT_THUMBPRINT
+  #   root_path: $SHAREPOINT_ROOT
+  #   with_metadata: true
+  #   refresh_interval: 30
+
+  # - !pw.io.gdrive.read
+  #   object_id: $DRIVE_ID
+  #   service_user_credentials_file: gdrive_indexer.json
+  #   name_pattern:
+  #     - "*.pdf"
+  #     - "*.pptx"
+  #   object_size_limit: null
+  #   with_metadata: true
+  #   refresh_interval: 30
+
+$llm: !pw.xpacks.llm.llms.OpenAIChat
+  model: "gpt-3.5-turbo"
+  retry_strategy: !pw.udfs.ExponentialBackoffRetryStrategy
+    max_retries: 6
+  cache_strategy: !pw.udfs.DiskCache
+  temperature: 0.05
+  capacity: 8
+
+$embedding_model: "mixedbread-ai/mxbai-embed-large-v1"
+
+$embedder: !pw.xpacks.llm.embedders.SentenceTransformerEmbedder
+  model: $embedding_model
+  call_kwargs: 
+    show_progress_bar: False
+
+$splitter: !pw.xpacks.llm.splitters.TokenCountSplitter
+  max_tokens: 400
+
+$parser: !pw.xpacks.llm.parsers.ParseUnstructured
+
+$retriever_factory: !pw.stdlib.indexing.BruteForceKnnFactory
+  reserved_space: 1000
+  embedder: $embedder
+  metric: !pw.internals.yaml_loader.import_object
+    path: pw.stdlib.indexing.BruteForceKnnMetricKind.COS
+  dimensions: 1536
+  
+
+document_store: !pw.xpacks.llm.document_store.DocumentStore
+  docs: $sources
+  parser: $parser
+  splitter: $splitter
+  retriever_factory: $retriever_factory
+
+
+# Change host and port by uncommenting these files
+# host: "0.0.0.0"
+# port: 8000
+
+# with_cache: true
+# terminate_on_error: false

examples/pipelines/demo-document-indexing/app.yaml

@@ -4,7 +4,7 @@ services:
     build:
       context: .
     ports:
-      - "8001:8000"
+      - "8000:8000"
     environment:
       OPENAI_API_KEY: "${OPENAI_API_KEY}"
     volumes: