Graphic Designer Newcastle Upon Tyne Projects
Looking for freelance Graphic Designer Newcastle Upon Tyne jobs and project work? PeoplePerHour has you covered.
opportunity
I need a YouTube animation intro and 3 thumbnail styles
My company has a YouTube channel and I want a professional intro animation and 3 thumbnail design templates created to match our branding. For the animation, I have an example I like here, https://youtu.be/kOkydX3g2Z4?si=A8cUdTo_PD-ftckN&t=4 from 4 seconds to 7 seconds. Just a screen which shows our company name and some nice looking graphics with motion and possibly some simple sound. I had thought about the idea of having an IT sound, like a clicking keyboard typing our logo out, a dot matrix printer sound or part of the old dial-up sound as we're an IT company. But I don't want it to get annoying and people to click away so maybe sound has to be very short or not that strong and more of just a ping/swoosh type sound. https://www.youtube.com/watch?v=rTWqUPQ9mTc https://www.youtube.com/watch?v=ZQTvcZH76Fk https://www.youtube.com/watch?v=gsNaR6FRuO0 Those are just some ideas we came up with but I would like something in our colour scheme and hopefully IT/techy related. In summary, I want a short animation intro of perhaps 2-3 seconds and 3 styles of thumbnails templates.
16 days ago39 proposalsRemoteA YouTube video intro and outro
We are expanding our popular audio podcast to YouTube, and we require the creation of a captivating video intro and outro to enhance the viewing experience for our audience. Our podcast features engaging content and a dedicated following, and we aim to replicate that success in the video format. To kickstart this project, we have already gathered a collection of graphics, including our logo and social media templates, which can serve as valuable inspiration for the video intro and outro. Additionally, we have pre-recorded audio idents that can be incorporated into the video to create a seamless and cohesive experience. We are seeking a talented freelancer with experience in video production to bring our vision to life. The ideal candidate should have a keen eye for design, a strong understanding of audio and video editing techniques, and the ability to work collaboratively with our team to achieve our goals. The video intro and outro should be approximately 10 seconds long each and should seamlessly integrate our graphics, audio idents, and any additional elements you may suggest. We are open to creative suggestions and are eager to work with you to create a visually stunning and memorable introduction and conclusion to our YouTube videos. If you are a passionate video producer with a track record of creating engaging content, we would love to hear from you. Please submit your portfolio and a proposal outlining your approach to this project, including your estimated timeline and cost. We look forward to collaborating with you to take our podcast to the next level on YouTube.
21 days ago28 proposalsRemoteNeural Radiance field
I seek a capable programmer to optimize code for Neural Radiance Field applications. The goal is to separate the existing PyTorch implementation into discrete training and inference modules for improved efficiency and deployment flexibility. Key tasks include refactoring the model and dataset code, designing clean APIs for the new modules, and testing the decoupled implementation matches original performance. Experience with graphics related deep learning, 3D representations, and PyTorch is preferred. The source is an open sourced academic project of interest for applications like novel view synthesis and 3D reconstruction. Candidates should demonstrate expertise in software architecture and optimization. Refactoring complex deep learning repos requires strong Python skills as well as understanding of underlying algorithms. This project aims to advance the capabilities of the NGP technique while preserving an accessible codebase for the research community. Willingness to engage in brief technical discussions is appreciated.
19 days ago8 proposalsRemoteLogo Designer for Dubai Events Company
We are a dynamic events company based in Dubai, specializing in curating unforgettable experiences in the realms of nightlife, beach club events, and brunches. As we continue to expand our brand presence, we are seeking a talented and creative logo designer to help us establish a distinctive visual identity. Responsibilities: Logo Design: Create a unique and visually appealing logo that encapsulates the essence of our events company, reflecting the excitement and vibrancy of Dubai's nightlife, beach club scene, and brunch culture. Concept Development: Work closely with our team to understand the brand's personality, target audience, and the unique elements of our events. Develop conceptual ideas that align with our vision. Style and Aesthetics: Design a logo that is modern, sophisticated, and versatile, with the ability to adapt across various mediums, including online platforms, merchandise, and event materials. Color Palette and Typography: Choose a suitable color palette and typography that complements the brand's image and resonates with our target audience. Requirements: Proven experience in logo design with a strong portfolio showcasing previous work. Creative flair and the ability to think outside the box to deliver unique and compelling design concepts. Familiarity with Dubai's nightlife, beach club events, and brunch culture to ensure the design aligns with the local scene. Proficient in graphic design tools such as Adobe Illustrator, Photoshop, or other industry-standard software. Strong communication skills to understand and incorporate feedback into design revisions. Budget: The budget for this logo design project is $80 How to Apply: If you're passionate about design and have a keen understanding of Dubai's dynamic events scene, we invite you to submit your proposal. Please include your portfolio, a brief introduction outlining your relevant experience, and how you plan to approach this project. Important Note: We value creativity and originality. Applicants are encouraged to showcase their unique design perspectives. The selected designer will not only have the opportunity to contribute to our brand's visual identity but will also be recognized for their work in our event promotions. We look forward to reviewing your proposals and finding a designer who can bring our vision to life. Best regards,
a month ago34 proposalsRemotePrepare + organize the visual assets needed for YouTube videos
We are hiring someone to prepare and organize the visual assets needed for YouTube videos. Your CORE RESPONSIBILITY will be: 1) Read the script for a given YouTube video, then use your best judgement as to what visual assets would be optimal for each section of the video. Then? 2) Prepare + collect these assets, as needed, and organize them into a Google Drive folder for our video editors. The videos on our channel primarily focus around Photoshop, graphic design, ecommerce, and related topics. The ultimate goal of each video is to provide concise, maximum value to the user while also sprinkling in a bit of fun/humor/entertainment. KEY REQUIREMENTS include: --Experience with the YouTube-video-creation process; --Graphic design / Photoshop skills + experience; --An active Photoshop subscription (a legitimate non-pirated Adobe Photoshop subscription is strongly preferred); --The ability to perform screen-recording videos which clearly and correctly demonstrate the appropriate/required actions for the viewer, on a clean and visually-uncluttered computer workspace (ie, you don't have 40 irrelevant tabs/windows open during the demo, etc); --Excellent instincts + judgement as to what visual assets would be optimal for a given video section; --Creativity, resourcefulness, + initiative, in terms of preparing the very best visual assets, so as to make the very best final video for the viewer. ADDITIONAL BONUS TRAITS include: --Good sense of humor and the ability to integrate a bit of fun/humor/entertainment into some of the visual assets as well. ORGANIZATION / EXPECTATIONS: --The visual assets for a given video will be organized into a dedicated Google Drive folder for that video. This folder will contain clearly-named sub-folders including SCREEN-RECORDING VIDEOS, SCREENGRAB IMAGES, STOCK VIDEOS, STOCK IMAGES, MIDJOURNEY IMAGES, CUSTOM IMAGES, and perhaps others if needed. --The filenames must be clear + descriptive, so our video editors can easily understand what each item demonstrates. "video-1.mp4" is a bad filename since it's unclear what that video illustrates. "create-new-smart-object-in-photoshop.mp4" and "how-to-use-psd-mockups-in-photoshop.mp4" is a clear, descriptive filename whose contents can be understood at a glance. --Items do not need to be excessively split up into tiny clips. (Example: Imagine the current video topic is "Best T-Shirt Mockup Websites", and one featured website is CreativeMarket.com. We wouldn't need separate video files for each little action performed on this website; one single screen-recording video showcasing the relevant actions on this website titled "creative-market-website-screen-recording.mp4" will be sufficient for our editors to scrub through to find the relevant clips) --The balance of needed/optimal assets will vary, from video-to-video. One video might be 90%+ screen-recording videos. Another might be more stock videos or custom images to visually illustrate certain concepts. The goal is NOT to arbitrarily fill the above folders with assets for each video just for the sake of filling each and every possible folder; the goal is instead to use your best judgement as to what visual assets are needed to make the very best video, then simply prepare those and only those required assets, and then conclude your prep for that video. --The ideal candidate will strike the best balance between, selecting/preparing the optimal assets for a given video—but NOT spending excessively massive amounts of time doing this for any one specific video. The goal is to select + curate an excellent pool of assets while ALSO working efficiently. LEGAL REQUIREMENTS: --If you create custom images/assets for a given video, you must be willing to provide us a "work for hire" / "copyright transfer" agreement, granting me + my company the copyright to use these assets in our YouTube videos (and perhaps in other marketing materials as well.) This will be a simple Google Document between us. --If you download stock videos or stock image assets, they must come from Storyblocks or Envato Elements, and you must provide the URL list of the specific assets you sourced/downloaded for each video. This will be a simple text document provided to us. POINTS OF CLARIFICATION: --Your responsibility here is NOT to edit together the final YouTube videos themselves; you are instead responsible for preparing the key visual assets for a given video. (Our video editors will take it from there to edit together the final video.) If hired, we will begin with a few paid trial projects. If you do an excellent job in this role, there is likely to be consistent, ongoing work in this position. Selected candidates will be provided with links to our recent YouTube videos to help understand the current video style, the visual assets commonly used, and how the balance of visual assets might vary based upon the video topic. Thank you!
3 hours ago2 proposalsRemoteopportunity
DWG File For Laser Cut Out
I require assistance in developing a digital file from existing architectural drawings to facilitate laser cutting of a custom steel enclosure. The drawings provided by our design team depict the overall form and structure of the storage bin we aim to produce. However, to precision cut the steel sheets using our laser fabrication equipment, a computer-generated CAD file in DWG format is needed. Specifically, the drawings include an image that must be recreated within the file to allow for its selective removal from the steel panels via the laser. A proficient CAD technician is sought to analyze the hand drawings and reconstruct the outlined shape as well as any identifying text, converting the outlined graphics into suitable vector form compatible with CAM software. Familiarity with laser cutting workflows and practices is preferable but not mandatory. This project requires translation of draft plans into digital engineering format through technical drafting expertise. The delivered files must accurately reflect all dimensions and design details from the physical drawings provided. Communication will be conducted through the client portal to maintain project focus. The short deadline reflects urgent production needs to meet an approaching exhibition date. Candidates with demonstrated experience in CAD conversion of architectural drawings to technical files for manufacturing are encouraged to apply.
23 days ago30 proposalsRemoteSpanish Translation of Graphic Designs (2433 Words)
Aim: seeking a Spanish translator to translate graphic designs from English to Spanish (2433 words to be translated in total) payment: $97 fixed price (please follow People Per Hour job posting rules). It is a one-time hiring Status: freelance hiring.
2 months ago42 proposalsRemoteopportunity
Pitch Deck
We are forming a group of companies in Timber supply and Biomass energy and are seeking a skilled Pitch Deck writer and designer to create a compelling and professional presentation that will help us raise finance. The Pitch Deck will showcase our business concept, market analysis, financial projections, and growth strategy, and will be used to attract investors and secure funding. The ideal candidate will have a strong understanding of financial markets, investment strategies, and business planning. They will have experience creating Pitch Decks for a variety of industries and will be able to translate complex data into easily understandable visuals and narratives. Responsibilities: - Write and design a comprehensive Pitch Deck that includes all relevant information about our business concept, market analysis, financial projections, and growth strategy. - Work closely with our team to gather and analyze data, and to develop a clear and compelling story that resonates with investors. - Create visually appealing and professional graphics and charts to support the narrative and enhance the overall presentation. - Ensure that the Pitch Deck is concise, clear, and easy to understand, and that it addresses any potential investor concerns or questions. - Prepare for and participate in investor meetings and pitch presentations. Requirements: - Strong experience in writing and designing Pitch Decks for a variety of industries. - Excellent communication and interpersonal skills. - Strong analytical and problem-solving skills. - Proficiency in financial modeling and analysis. - Ability to work independently and as part of a team. - Strong attention to detail. If you are a skilled Pitch Deck writer and designer with a passion for entrepreneurship and a track record of success, we would love to hear from you. Please submit your resume and a sample of your work for consideration.
a month ago19 proposalsRemoteInspire heating & plumbing services ltd
Inspire heating & plumbing services ltd is seeking an experienced freelance writer to refresh content across their website and online marketing material. The company provides home heating, cooling and plumbing installation and repair services across London. The selected freelancer will be responsible for rewriting web pages and case studies to capture more engaging storytelling and ensure information remains fresh and relevant. Key tasks will include enhancing descriptions of the core services offered to better convey company expertise and passion for customer satisfaction. Blog posts covering common plumbing and HVAC issues will need revision to use more approachable language. Additionally, copy for social media, email campaigns and digital advertisements will be assessed. The goal is to maintain a consistent brand voice while optimizing for key search terms and calls-to-action. Graphic design skills are not required but the ability to clearly communicate technical topics to a non-expert audience is essential. The successful candidate will have 3-5 years experience creating website content and online marketing materials for trades businesses. Examples of previous work samples rewriting technical B2C materials for companies in the home services or construction industries would be beneficial. Rates will be negotiated based on portfolio and availability over the next 6 months. This is a remote freelance role.
17 days ago16 proposalsRemoteOnline research/analytics keywords from 2014 to '23
Am needing help producing a report of the mentions of some healthcare related key phrases over the last 12 years. The phrases are: Patient Centricity and Patients at the Centre (see below other search terms) The analysis of historical data of mentions (going back this far) will be a challenge - but I am open to considering potential proxy analysis instead. Re Social Media - Conducting this research might on X/Twitter is not as easy as it used to be (and involves now a higher cost). But happy to review and agree on joint plan. Country/scope: English speaking countries only (at first) Outputs: I require basic spreadsheets or visual reports to be used in a presentation ( graphic design work will be done via someone else). Assuming some success in producing a picture of usage of these terms, I then have a separate bit of work, regarding COVID 19, and media coverage of 2-3 pharma companies. This is quite a narrow brief, dealing with a 2-3 year time frame only. This separate bit of research is related to the above. KEYWORDS: keywords = [ "Patient centric", "Patient Centric", "Patient First", "Patient at the centre", "Patient at the center", "Patient at the centre of everything we do", "Patient at the center of everything we do", "Patient at the centre of all we do", "Patient at the center of all we do", "Patient Centricity", "Patient centricity"
a month ago18 proposalsRemoteopportunity
Existing website redesign
Hello! I'm looking for someone to redesign one of our websites. Design, graphics design and function changes are all needed. I'm looking more for a long time relationship with the developer / agency because there are other tasks and websites are in the pipeline, so a month or week based quote would be nice. Used frameworks, languages and software: Backend: PHP 7.4.33, Laravel 8, MariaDB Frontend: HTML, CSS, Javascript-JQuery Server: Debian 11 Website: https://vip.maxlomp.com/ What I would like to change on the website: The whole website should be usable both from desktop computer and mobile phone. Home page: - some of the text needs to be changed for sure, but I can do that on my own - the design should be changed, especially the mobile version, right now there is no incentive for a visitor to proceed with registration or anything Menu page / movie scene list: - because we will have much more movie scenes here (around 200) we will need paging, show 10 movies on each page - the design should be much better, right now it is uninteresting and too simple - we should be able to show title, short description, length, main image, 2-4 images for each individual movie - I also need a ?block? to the top of the website where we can put marketing messages, image slider etc. like we are doing on graias.com now - if they click on the movie title or the images or a button they should be linked to the movie sub page - there should be a “Watch this” button which will bring you to the membership purchase page next to each movie (if he is already a member just go to the movie subpage where they can actually watch it) - good example: https://graias.com/preview Movie details subpage: - we need such a page for every movie we will have on VIP MaxLomp - a good example of what we are looking for: - https://graias.com/video/healing-pain---part-2/337 - we need to show: title, description and length of movie, trailer video, gallery of images - if he doesn’t have an active membership there should be a button here that sends him to the membership purchase page - if he has an active membership he can watch the movie here (streaming inside the website), for this the video streaming server is already finished only embedding the streaming link is necessary Membership purchase page: - here a logged in user can select 3 types of memberships (one month, three month, one year) and request payment details for such a membership (right now we do Paypal, Bank transfer and Crypto payments) - so there are 3 types of membership and 3 different way to pay for them - there should be ample room to add marketing text to the page also where we tell them about what we offer, the different memberships etc. - kind of good example: https://graias.com/subscribe What we already have for sure and no need to code it again: - streaming server for movie playback - the way to handle payments (we can discuss this later) We also have the source code of the website and the database. Because this is a website that already works the migrations for the website should take this into consideration (do not delete anything but alter for new needs).
a month ago45 proposalsRemoteAgency or designer/video maker
Fight for Humanity: Founded in March 2019, Fight for Humanity is a Swiss-based non-governmental organization that seeks to reinforce respect for the rights of people exposed to human rights abuses in situations of violence and conflict. It currently implements programs in the Middle East on child protection, the protection of cultural heritage, and peace and social cohesion. Context : Fight for Humanity has been mandated by CARE to develop an Educational Material Package based on a document recently developed called the “Practical Measures Project to Prevent and Mitigate Conflict-Induced Hunger”. States, armed groups, humanitarian/human rights actors, and other civil society and community-based organizations actors will use the material package to better understand, apply, and communicate about the Practical Measures. The package includes a training module, a video, visuals, and a flyer. Objective: Fight for Humanity is looking for an agency or designer/video maker to produce: 8 impactful social media visuals mixing short text and illustrations that can be used to advocate the main messages through social media campaigning. They can also be adapted as stickers. One short video (max. 1 minute) with animated images that can be used during events or online. The soundtrack of the video will include a voice over and music and can also be adapted as radio message when relevant locally. One short and catchy flyer that includes short text and illustrations that could also be adapted into a poster (Infographic). Target audience: Armed actors, both state armed forces and non-state armed groups Humanitarian/human rights actors Civil society and community-based organizations Because the target audiences are so diverse, the material should deliver simple and powerful messages, that would be general enough to be understood in different countries affected by armed conflict. Possible dissemination channels : Social media in the relevant countries Training sessions organized by international or local actors Distribution of flyers and display of the poster General guidelines : There should be a consistency between the videos and the visuals. The material should be positive: it should be colorful and with illustrations that are simple and clear to understand. The material should be in English but might be adapted in other languages when required. The illustrations should mix a wide range of country settings, colors of skin and ethnic background to be used in different countries, examples can be provided. Messages: For the video (animated images), it should quickly present: The link between conflict and hunger and the situation in conflict affected countries. The damage that armed actors can cause to food production and distribution (fields, markets, transport, etc.). Positive measures that armed actors can take to prevent and mitigate food insecurity (selection of the most important practical measures). For the 8 visuals: Each visual should present one clear practical measure through one image with a message. Flyer and poster: They will be built as an infographic with figures and diagrams to present: The link between conflict and hunger and the situation in conflict-affected countries. The damage that armed actors can cause to food production and distribution (fields, markets, transport etc.). Some of the most important practical measures (use of some of the illustrations developed for the visuals). This would be organized in a poster and flyer. Timeline: 1st March - 15th March: procurement and selection of one or two service providers (potentially one video-maker and one graphic designer or alternatively one agency) definition of a draft video script and the 8 messages for the visuals with the project team including consultation with CARE 18 March – 27 March Briefing of the selected service providers Discussion on the script and messages and adaptations if necessary Sharing examples 5 April First storyboard ready for the video First draft of the infographics structure 8 - 12 April Consultation with CARE and the project team to finalize the video final storyboard and the infographic structure Final storyboard ready on 12 April, final structure of the infographics ready 15 April – 10 May Development of the video Sound recording Animation development Titles In parallel, preparation of the 8 visuals and consultations for potential modifications 10 May - 20 May First draft of video ready on 10 May Consultations for minimal modifications Final version of the video and visuals ready on 20 May Finalization of the infographics with the visuals How to apply: Please send a quote and references to info@fightforhumanity.org with the reference “Video design” no later than 17 March 2024. Only complete applications will be considered. Please note that only shortlisted candidates/agencies will be contacted.
22 days ago11 proposalsRemoteopportunity
Automated Semantic Text Analysis Pipeline
Comprehensive Use Case Specification: Automated Semantic Text Analysis Pipeline Objective Develop an automated semantic text analysis pipeline that processes and analyses textual data extracted from documents. This pipeline enriches text with metadata for deeper insights and enables semantic search capabilities through a user-friendly interface. This stage of the project is for a MVP system should leverage AWS services such as Textract for text extraction, a text categorising stage with a simple to use GUI, all-mpnet-base-v2 for embedding, and Postgres with a vector extension. This job posting is for the MPV stage only, but we must be mindful of the stage two development and facilitate rapid and straightforward scalability in any stage one MPV processes. System Overview The solution encompasses AWS services for storage and processing, a custom interface for metadata enrichment, all-mpnet-base-v2 for generating text embeddings, Postgres and a vector extension for efficient storage and retrieval of vectors, and a custom-built web interface for user interaction. RAG will be implemented with a broad a context as possible to the model across a large document set. Phase 1: MVP Stage 1. Document Storage and Processing Trigger - Tool: Amazon S3. - Process: Upload documents (PDFs initially) to designated S3 buckets, documents will be remained in accordance with a set naming convention and key metadata relating to the document entered into the database for future reference. This triggers the subsequent text extraction process. For test purposes the uploads will be made manually, and at later stages a web scraper will be added that automatically places PDF documents into relevant S3 buckets. 2. Text Extraction - Tool: AWS Textract. - Process: Text is extracted from uploaded PDF documents and temporarily stored in A3 buckets to facilitate further processing. 3. Text Enrichment Developer to advise on best method of adding labels / categories to the text, via an easy to use interface. Labels to be added at a granular level to allow the return of text snippets, providing context to the LLM in formulating it's responses from a broad range of documents without exceeding the token limit. 4. Text Vectorization - Embedding tool: all-mpnet-base-v2 - LLM: Amazon SageMaker (using LLaMA 2). - Process: The text is processed with LLaMA 2 to generate vector embeddings, capturing semantic information for advanced analysis and search functionalities. 5. Vector Storage - Tool: Postgres with a vector extension - Process: Text vectors are stored in the database, allowing for efficient management and retrieval of vectorized data for semantic searches. 6. Front-end Web Application and Search Functionality - Front-end Technology: React.js. - Key Features: - Semantic search input and results display. - email input field for collecting contact information for marketing purposes, forwarding to the client's email address. - Homepage containing descriptive marketing text. - 3 pages total: home page, interaction page, contact page, plus a pop up with GDPR info. Graphics provided as template guidance. - Back-end Technology: Python with FastAPI. Phase 2: Full Automation and Scaling 1. Automated Document Ingestion - Process: A web scraping tool is implemented to automatically identify and upload new documents to the S3 bucket, facilitating a continuous flow of data into the pipeline without manual intervention. 2. Scalable Architecture - Deployment: The application components are containerized using Docker and managed with Kubernetes (Amazon EKS), ensuring the system can scale efficiently to accommodate increased data volumes and user queries. 3. Enhanced Processing Capabilities - Improvements: Integrate additional NLP and ML models for broader and more nuanced text analysis. Consider fine-tuning custom models for specific domain applications. 4. User registration and user management system integration. Please note the attached contract agreement that will be deemed agreed to upon acceptance of the project. Your price given on PPH will be deemed to be your full and final price, and you will be deemed to have fully understood the scope, brief, and specification. To provide context, the project business plan has been uploaded. This is for context only and does not form part of the brief.
22 days ago11 proposalsRemoteopportunity
Local Council Chatbot utilising Llama2 and dataset of PDF docs.
Full stack developer with relevant experience in AWS services and LLM deployment. Description Develop an MVP that provides a chat interface allowing users to query a dataset of local council documents, which will variously include minutes and policy documents. A dataset that contains all information relating to the purpose, policies, news, information, and decision making by that council. The dataset would contain approximately 100 PDF documents, and the chatbot would return meaningful and coherent answers to user prompts, while providing reference links to documents that information in the response is taken from. The client acknowledges the current limitations of LLMs in returning responses from queries across multiple documents, especially given current token limits and processing cost restrictions. A developer is sought that can leverage techniques to embed metadata in the text, allowing techniques such as RAG to extract snippets of data from multiple documents relating to the query and collate them into a response to the user, while adhering to token limits. Objective Develop an automated semantic text analysis pipeline that processes and analyses textual data extracted from documents using Llama2. This pipeline enriches text with metadata for deeper insights and enables semantic search capabilities through a user-friendly interface. This stage of the project is for a MVP system, leveraging AWS services such as Textract for text extraction, a text categorising stage with a simple to use GUI, all-mpnet-base-v2 for embedding, and Postgres with a vector extension. This job posting is for the MPV stage only, but we must be mindful of the stage two development and facilitate rapid and straightforward scalability in any stage one MPV processes. System Overview The solution encompasses AWS services for storage and processing, a custom interface for metadata enrichment, all-mpnet-base-v2 for generating text embeddings, Postgres and a vector extension for efficient storage and retrieval of vectors, and a custom-built web interface for user interaction. RAG will be implemented with a broad a context as possible to the model across a large document set. Phase 1: MVP Stage 1. Document Storage and Processing Trigger Tool: Amazon S3. Process: Upload documents (PDFs initially) to designated S3 buckets, documents will be renamed in accordance with a set naming convention and details of the document entered into the database. This triggers the subsequent text extraction process. For test purposes the uploads will be made manually, and at later stages a web scraper will be added that automatically places PDF documents into relevant S3 buckets. 2. Text Extraction - Tool: AWS Textract. - Process: Text is extracted from uploaded PDF documents and temporarily stored in A3 buckets to facilitate further processing. 3. Text Enrichment Developer to advise on best method of adding labels / categories to the text, via an easy to use interface. Labels to be added at a granular level to allow the return of text snippets from within the chunks of data, but with relevant metadata. The purpose of this is to provide context to the LLM in formulating responses from a broad range of documents without exceeding the token limit. 4. Text Vectorization • Embedding tool: all-mpnet-base-v2 • LLM: Amazon SageMaker (using LLaMA 2). Process: The text is processed with LLaMA 2 to generate vector embeddings, capturing semantic information for advanced analysis and search functionalities. 5. Vector Storage Tool: Postgres with a vector extension Process: Text vectors are stored in the database, allowing for efficient management and retrieval of vectorized data for semantic searches. 6. Front-end Web Application and Search Functionality Front-end Technology: • React.js. Key Features: • Semantic search input and results display. • email input field for collecting contact information for marketing purposes, forwarding to the client's email address. • Homepage containing descriptive marketing text. 3 pages total: home page, interaction page, contact page, plus a pop up with GDPR info. Graphics provided as template guidance. Back-end Technology: • Python with FastAPI. 7. Fine Tuning Allow for fine tuning based on a series of questions and responses to be provided by the client, until such point that coherent responses to queries are achieved. Phase 2: Full Automation and Scaling Beyond the scope of this job. Notes: The developer is to provide guidance and feedback on the capabilities of the technologies and is free to provide their own guidance and suggestions. However, the functionality of the system in providing coherent responses based on text snippets drawn from a large dataset is both the challenge and the absolute requirement. Please only bid with your full and final price. Placeholders will not be accepted. Completion with approximately two weeks. Please respond by explaining how you would handle the text enrichment?
22 days ago17 proposalsRemote