opea-project
diff --git a/‎comps/cores/proto/docarray.py
Lines changed: 1 addition & 0 deletions b/‎comps/cores/proto/docarray.py
Lines changed: 1 addition & 0 deletions
diff --git a/‎comps/dataprep/milvus/prepare_doc_milvus.py
Lines changed: 1 addition & 0 deletions b/‎comps/dataprep/milvus/prepare_doc_milvus.py
Lines changed: 1 addition & 0 deletions
diff --git a/‎comps/embeddings/multimodal_clip/README.md
Lines changed: 52 additions & 0 deletions b/‎comps/embeddings/multimodal_clip/README.md
Lines changed: 52 additions & 0 deletions
diff --git a/‎comps/embeddings/multimodal_clip/__init__.py
Lines changed: 2 additions & 0 deletions b/‎comps/embeddings/multimodal_clip/__init__.py
Lines changed: 2 additions & 0 deletions
diff --git a/‎comps/embeddings/multimodal_clip/docker/Dockerfile
Lines changed: 29 additions & 0 deletions b/‎comps/embeddings/multimodal_clip/docker/Dockerfile
Lines changed: 29 additions & 0 deletions
diff --git a/‎comps/embeddings/multimodal_clip/docker/docker_compose_embedding.yaml
Lines changed: 22 additions & 0 deletions b/‎comps/embeddings/multimodal_clip/docker/docker_compose_embedding.yaml
Lines changed: 22 additions & 0 deletions
diff --git a/‎comps/embeddings/multimodal_clip/embedding_multimodal.py
Lines changed: 86 additions & 0 deletions b/‎comps/embeddings/multimodal_clip/embedding_multimodal.py
Lines changed: 86 additions & 0 deletions
diff --git a/‎comps/embeddings/multimodal_clip/embeddings_clip.py
Lines changed: 50 additions & 0 deletions b/‎comps/embeddings/multimodal_clip/embeddings_clip.py
Lines changed: 50 additions & 0 deletions
diff --git a/‎comps/embeddings/multimodal_clip/requirements.txt
Lines changed: 14 additions & 0 deletions b/‎comps/embeddings/multimodal_clip/requirements.txt
Lines changed: 14 additions & 0 deletions
diff --git a/‎comps/finetuning/README.md
Lines changed: 6 additions & 0 deletions b/‎comps/finetuning/README.md
Lines changed: 6 additions & 0 deletions
@@ -64,6 +64,7 @@ class EmbedDoc(BaseDoc):
     fetch_k: int = 20
     lambda_mult: float = 0.5
     score_threshold: float = 0.2
+    constraints: Optional[Union[Dict[str, Any], None]] = None
 
 
 class EmbedMultimodalDoc(EmbedDoc):
 
@@ -133,6 +133,7 @@ def ingest_data_to_milvus(doc_path: DocPath, embedder):
         )
 
     content = document_loader(path)
+
     if logflag:
         logger.info("[ ingest data ] file content loaded")
 
 
@@ -0,0 +1,52 @@
+# Multimodal CLIP Embeddings Microservice
+
+The Multimodal CLIP Embedding Microservice is designed to efficiently convert textual strings and images into vectorized embeddings, facilitating seamless integration into various machine learning and data processing workflows. This service utilizes advanced algorithms to generate high-quality embeddings that capture the semantic essence of the input text and images, making it ideal for applications in multi-modal data processing, information retrieval, and similar fields.
+
+Key Features:
+
+**High Performance**: Optimized for quick and reliable conversion of textual data and image inputs into vector embeddings.
+
+**Scalability**: Built to handle high volumes of requests simultaneously, ensuring robust performance even under heavy loads.
+
+**Ease of Integration**: Provides a simple and intuitive API, allowing for straightforward integration into existing systems and workflows.
+
+**Customizable**: Supports configuration and customization to meet specific use case requirements, including different embedding models and preprocessing techniques.
+
+Users are albe to configure and build embedding-related services according to their actual needs.
+
+## 🚀1. Start Microservice with Docker
+
+### 1.1 Build Docker Image
+
+#### Build Langchain Docker
+
+```bash
+cd ../../..
+docker build -t opea/embedding-multimodal:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/multimodal_clip/docker/Dockerfile .
+```
+
+### 1.2 Run Docker with Docker Compose
+
+```bash
+cd comps/embeddings/multimodal_clip/docker
+docker compose -f docker_compose_embedding.yaml up -d
+```
+
+## 🚀2. Consume Embedding Service
+
+### 2.1 Check Service Status
+
+```bash
+curl http://localhost:6000/v1/health_check\
+  -X GET \
+  -H 'Content-Type: application/json'
+```
+
+### 2.2 Consume Embedding Service
+
+```bash
+curl http://localhost:6000/v1/embeddings \
+      -X POST   -d '{"text":"Sample text"}' \
+      -H 'Content-Type: application/json'
+
+```
@@ -0,0 +1,2 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
@@ -0,0 +1,29 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+FROM langchain/langchain:latest
+
+ARG ARCH="cpu"
+
+RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
+    libgl1-mesa-glx \
+    libjemalloc-dev \
+    vim
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user/
+
+USER user
+
+COPY comps /home/user/comps
+
+RUN pip install --no-cache-dir --upgrade pip && \
+    if [ ${ARCH} = "cpu" ]; then pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu; fi && \
+    pip install --no-cache-dir -r /home/user/comps/embeddings/multimodal_clip/requirements.txt
+
+ENV PYTHONPATH=$PYTHONPATH:/home/user
+
+WORKDIR /home/user/comps/embeddings/multimodal_clip
+
+ENTRYPOINT ["python", "embedding_multimodal.py"]
@@ -0,0 +1,22 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+version: "3.8"
+
+services:
+  embedding:
+    image: opea/embedding-multimodal:latest
+    container_name: embedding-multimodal-server
+    ports:
+      - "6000:6000"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
+    restart: unless-stopped
+
+networks:
+  default:
+    driver: bridge
@@ -0,0 +1,86 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+import datetime
+import os
+import time
+from typing import Union
+
+from dateparser.search import search_dates
+from embeddings_clip import vCLIP
+
+from comps import (
+    EmbedDoc,
+    ServiceType,
+    TextDoc,
+    opea_microservices,
+    register_microservice,
+    register_statistics,
+    statistics_dict,
+)
+
+
+def filtler_dates(prompt):
+
+    base_date = datetime.datetime.today()
+    today_date = base_date.date()
+    dates_found = search_dates(prompt, settings={"PREFER_DATES_FROM": "past", "RELATIVE_BASE": base_date})
+
+    if dates_found is not None:
+        for date_tuple in dates_found:
+            date_string, parsed_date = date_tuple
+            date_out = str(parsed_date.date())
+            time_out = str(parsed_date.time())
+            hours, minutes, seconds = map(float, time_out.split(":"))
+            year, month, day_out = map(int, date_out.split("-"))
+
+        rounded_seconds = min(round(parsed_date.second + 0.5), 59)
+        parsed_date = parsed_date.replace(second=rounded_seconds, microsecond=0)
+
+        iso_date_time = parsed_date.isoformat()
+        iso_date_time = str(iso_date_time)
+
+        if date_string == "today":
+            constraints = {"date": ["==", date_out]}
+        elif date_out != str(today_date) and time_out == "00:00:00":  ## exact day (example last friday)
+            constraints = {"date": ["==", date_out]}
+        elif (
+            date_out == str(today_date) and time_out == "00:00:00"
+        ):  ## when search_date interprates words as dates output is todays date + time 00:00:00
+            constraints = {}
+        else:  ## Interval  of time:last 48 hours, last 2 days,..
+            constraints = {"date_time": [">=", {"_date": iso_date_time}]}
+        return constraints
+
+    else:
+        return {}
+
+
+@register_microservice(
+    name="opea_service@embedding_multimodal",
+    service_type=ServiceType.EMBEDDING,
+    endpoint="/v1/embeddings",
+    host="0.0.0.0",
+    port=6000,
+    input_datatype=TextDoc,
+    output_datatype=EmbedDoc,
+)
+@register_statistics(names=["opea_service@embedding_multimodal"])
+def embedding(input: TextDoc) -> EmbedDoc:
+    start = time.time()
+
+    if isinstance(input, TextDoc):
+        # Handle text input
+        embed_vector = embeddings.embed_query(input.text).tolist()[0]
+        res = EmbedDoc(text=input.text, embedding=embed_vector, constraints=filtler_dates(input.text))
+
+    else:
+        raise ValueError("Invalid input type")
+
+    statistics_dict["opea_service@embedding_multimodal"].append_latency(time.time() - start, None)
+    return res
+
+
+if __name__ == "__main__":
+    embeddings = vCLIP({"model_name": "openai/clip-vit-base-patch32", "num_frm": 4})
+    opea_microservices["opea_service@embedding_multimodal"].start()
@@ -0,0 +1,50 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+import torch
+import torch.nn as nn
+from einops import rearrange
+from transformers import AutoProcessor, AutoTokenizer, CLIPModel
+
+model_name = "openai/clip-vit-base-patch32"
+
+clip = CLIPModel.from_pretrained(model_name)
+processor = AutoProcessor.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+
+class vCLIP(nn.Module):
+    def __init__(self, cfg):
+        super().__init__()
+
+        self.num_frm = cfg["num_frm"]
+        self.model_name = cfg["model_name"]
+
+    def embed_query(self, texts):
+        """Input is list of texts."""
+        text_inputs = tokenizer(texts, padding=True, return_tensors="pt")
+        text_features = clip.get_text_features(**text_inputs)
+        return text_features
+
+    def get_embedding_length(self):
+        return len(self.embed_query("sample_text"))
+
+    def get_image_embeddings(self, images):
+        """Input is list of images."""
+        image_inputs = processor(images=images, return_tensors="pt")
+        image_features = clip.get_image_features(**image_inputs)
+        return image_features
+
+    def get_video_embeddings(self, frames_batch):
+        """Input is list of list of frames in video."""
+        self.batch_size = len(frames_batch)
+        vid_embs = []
+        for frames in frames_batch:
+            frame_embeddings = self.get_image_embeddings(frames)
+            frame_embeddings = rearrange(frame_embeddings, "(b n) d -> b n d", b=len(frames_batch))
+            # Normalize, mean aggregate and return normalized video_embeddings
+            frame_embeddings = frame_embeddings / frame_embeddings.norm(dim=-1, keepdim=True)
+            video_embeddings = frame_embeddings.mean(dim=1)
+            video_embeddings = video_embeddings / video_embeddings.norm(dim=-1, keepdim=True)
+            vid_embs.append(video_embeddings)
+        return torch.cat(vid_embs, dim=0)
@@ -0,0 +1,14 @@
+dateparser
+docarray[full]
+einops
+fastapi
+huggingface_hub
+langchain
+open_clip_torch
+opentelemetry-api
+opentelemetry-exporter-otlp
+opentelemetry-sdk
+prometheus-fastapi-instrumentator
+sentence_transformers
+shortuuid
+uvicorn
@@ -92,10 +92,12 @@ Assuming a training file `alpaca_data.json` is uploaded, it can be downloaded in
 
 ```bash
 # upload a training file
+
 curl http://${your_ip}:8015/v1/finetune/upload_training_files -X POST -H "Content-Type: multipart/form-data" -F "files=@./alpaca_data.json"
 
 # create a finetuning job
 curl http://${your_ip}:8015/v1/fine_tuning/jobs \
+
   -X POST \
   -H "Content-Type: application/json" \
   -d '{
@@ -104,18 +106,22 @@ curl http://${your_ip}:8015/v1/fine_tuning/jobs \
   }'
 
 # list finetuning jobs
+
 curl http://${your_ip}:8015/v1/fine_tuning/jobs   -X GET
 
 # retrieve one finetuning job
 curl http://localhost:8015/v1/fine_tuning/jobs/retrieve   -X POST   -H "Content-Type: application/json"   -d '{
+
     "fine_tuning_job_id": ${fine_tuning_job_id}}'
 
 # cancel one finetuning job
 
+
 curl http://localhost:8015/v1/fine_tuning/jobs/cancel   -X POST   -H "Content-Type: application/json"   -d '{
     "fine_tuning_job_id": ${fine_tuning_job_id}}'
 
 # list checkpoints of a finetuning job
 curl http://${your_ip}:8015/v1/finetune/list_checkpoints -X POST -H "Content-Type: application/json" -d '{"fine_tuning_job_id": ${fine_tuning_job_id}}'
 
+
 ```
Original file line number	Diff line number	Diff line change
`@@ -133,6 +133,7 @@ def ingest_data_to_milvus(doc_path: DocPath, embedder):`
`133`	`133`	`)`
`134`	`134`
`135`	`135`	`content = document_loader(path)`
	`136`	`+`
`136`	`137`	`if logflag:`
`137`	`138`	`logger.info("[ ingest data ] file content loaded")`
`138`	`139`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,2 @@`
	`1`	`+# Copyright (C) 2024 Intel Corporation`
	`2`	`+# SPDX-License-Identifier: Apache-2.0`