alexcg1

from docarray import Document, DocumentArray
from jina import Executor, requests
from transformers import AutoModelForCausalLM, AutoTokenizer


class StableLM(Executor):
    def __init__(self, **kwargs):
        super().__init__(**kwargs)
        self.tokenizer = AutoTokenizer.from_pretrained(
            'StabilityAI/stablelm-base-alpha-3b'

alexcg1

DeprecationWarning: Deprecated call to `pkg_resources.declare_namespace('google')`.
Implementing implicit namespace packages (as specified in PEP 420) is preferred to `pkg_resources.declare_namespace`. See https://setuptools.pypa.io/en/latest/references/keywords.html#keyword-namespace-packages (raised from /mnt/data/work/repos/scene-alexcg/env/lib/python3.10/site-packages/pkg_resources/__init__.py:2804)
DeprecationWarning: Deprecated call to `pkg_resources.declare_namespace('google.logging')`.
Implementing implicit namespace packages (as specified in PEP 420) is preferred to `pkg_resources.declare_namespace`. See https://setuptools.pypa.io/en/latest/references/keywords.html#keyword-namespace-packages (raised from /mnt/data/work/repos/scene-alexcg/env/lib/python3.10/site-packages/pkg_resources/__init__.py:2804)
DeprecationWarning: Deprecated call to `pkg_resources.declare_namespace('google')`.
Implementing implicit namespace packages (as specified in PEP 420) is preferred to `pkg_resources.declare_namespace`. 

alexcg1

from docarray import BaseDoc, DocArray
from docarray.documents import TextDoc
from docarray.typing import AnyUrl
from jina import Deployment, Executor, requests


class TextChunk(TextDoc):
    tags: dict = {}

alexcg1

with flow:
  client = Client(port=flow.port)
  indexed_docs = client.post("/index", docs, request_size=1, show_progress=True, target_executor="(index_*|all_*)")

alexcg1

print(response[0].matches.texts)

alexcg1

response = client.search(search_doc)

alexcg1

from docarray import Document

search_doc = Document(text="statistic visualization")

alexcg1

from jina import Client

client = Client(host="grpcs://<unique_id>.wolf.jina.ai")  # Your gateway from earlier
client.index(docs, show_progress=True)

alexcg1

from docarray import DocumentArray

docs = DocumentArray.from_csv("Questions.csv", field_resolver={"Title": "text"})

alexcg1

jtype: Flow
with:
  protocol: grpc
executors:
  - name: encoder
    uses: jinahub+docker://SpacyTextEncoder/v0.4
    uses_with:
      model_name: 'en_core_web_md'
    resources:
      memory: 8G  # encoding is hungry. add more memory