o !6i @sddlZddlZddlZddlZddlZddlZddlmZmZddl m Z m Z ddl m Z ddl mZmZmZmZmZmZddlZddlZddlZddlZddlZddlmZeedZedd Zed Zed d Zed dZddl m!Z"ddl m#Z#ddl$m%Z%ej&ej'dde(e)Z*dZ+dZ,eZ-edZ.eddZ/ej0e-dZ1e"j2ddZ3eZ4d Z5e%eedZ$GdddZ6GdddZ7d d!Z8d"d#Z9d`d$ed%eefd&d'Z:d(e;d%eefd)d*Zd0e;d%e;fd1d2Z?d3d4Z@d`d5e;d6e;d7e;d8eee;efd%e;f d9d:ZAd`d;edd?ZBd`d;ed/var/www/html/minaions-tender/ai-engine/bid_prep_automation.pyr9src@s eZdZdZdZdZdZdZdS) DocumentTypestandard experiencecustomannexure regeneratedN)rr r!STANDARD EXPERIENCECUSTOMANNEXURE REGENERATEDr,r,r,r-r.Es r.c Cszt|dD}t|}t|j}d}t}|D]+}d|kr#|kr:nn|j|d} || d7}|| qtd|dqWdn1sMwYt|d } || Wdn1sgwY|rq|WSd } t|d }| } Wdn1swYt j j j d d d d dd| ddddt| dddgdgd} | jdj}|WStytd|YdSty}ztd|WYd}~dSd}~ww)a# Extracts text from specified pages of a PDF. Args: pdf_path (str): Path to the PDF file. page_numbers (list): List of page numbers to extract (1-based indexing). Returns: str: Concatenated text from the specified pages, or None if an error occurs. rb z Page number z is out of range. Skipping.Nwba This message contains scanned pages from a PDF document which will contain a format or annexure. For EACH PAGE, extract ALL text content visible in it along with its formatting information like tables etc. For preserving the tables formatting, you may use underscores '_' and pipe '|' symbols. NOTE that the text in the scanned pages can be in any language. zclaude-haiku-4-5皙?zYou are an expert at extracting annexure or table content from scanned documents. Extract ALL text visible on EACH page, preserving the original formatting as much as possible.usertexttyperAdocumentbase64application/pdfutf-8rC media_typedatarCsourcerolecontentmodel max_tokens temperaturesystemmessagesrzError: PDF file not found at zAn error occurred: )openrlenpagesr extract_textadd_pageprintwritereadself claude_clientrUcreaterE b64encodedecoderOrAFileNotFoundError Exception)pdf_path page_numbers output_pathpdf_filereader num_pagesextracted_textwriterpage_numpageout_fileprompt pdf_contentresponseer,r,r-get_annexure_contentMsh        rtc Cstj|s td|t|d }|}Wdn1s!wYd|d}tjjt dddd d |d d d dt | dddgdgd}|j djS)am Generates PDF-compatible HTML based on text content and formatting from a reference PDF. Args: doc_text (str): Raw text content to be formatted pdf_path (str): Path to reference PDF for formatting guidance Returns: str: Generated HTML code Raises: FileNotFoundError: If PDF file doesn't exist zReference PDF not found: r9NzAnalyze the attached reference format and styling of a document in the PDF and create PDF-compatible HTML for this text content: a Follow these exact requirements: 1. Layout Analysis: - Study the reference PDF's structure (headers, margins, spacing) - Identify font styles (sizes, families, weights) through visual patterns - Note paragraph spacing and indentation rules 2. Formatting Rules: - Preserve ALL original text styling (bold/italic/underline) using semantic HTML - Maintain EXACT table structures from reference (columns, borders, alignment) - Replicate list formatting (bullet styles, numbering, indentation) 3. HTML Requirements: - Use A4 page size: - Tables: Use with inline CSS for borders/padding - Placeholders: fill_data_here - Lists: Convert bullets to
    with 1em left margin - Headers: Match hierarchy (h1-h6) from reference 4. Output Constraints: - No markdown, ONLY HTML/CSS - Include complete document structure - Ensure print compatibility with PDF converters - Preserve white-space: pre-wrap for code blocks Return ONLY the HTML code with no additional commentary.r>r?zuYou are a professional document formatting expert specializing in PDF-to-HTML conversion with pixel-perfect accuracy.r@rArBrDrErFrGrHrKrMrPr)ospathexistsrcrVr]r_rUr`claude_model_mainrErarbrOrA)doc_textrerhrqrprrr,r,r-document_formattings8   " rzextracted_inforeturnc Cs(|durt} |ddd}|r|dkrtdgS|ddd}|ddd}d|r5|dd nd d |r@|dd nd d |d}z)tdkrttjjtddddddd|dgd}|d|j dj |j dj }ntdkrt j jjtdddd|dgd}|jdjj }td|tj}|r|d} nAtd|tj}|r|d} n1|d } g} d!} | D]} | d"s| rd#} | | | d$rnq| rd | } n|} | } | d"sd"| } | d$s| d$} zt| }Wntjy|d%t|}Ynw|d&t |d't!|D]M\}}|d(|dd)|d*d+d,|d-d+|d-t"j#krn|d.rnd/}t$||d.tj%}|rc|d|d.<|d0|d.q"|WSt&y}zt'd1t(|t)|WYd}~Sd}~ww)2N"Documents needed to submit the bidr:rOzNot found in any documentz7No document requirements found in extracted information"Scope of work of the whole project;Eligibility/Qualification Criteria or conditions for biddera+ You are an expert in government tender document preparation. I'll provide you with text describing document requirements for a tender bid. Analyze this text and extract a structured list of all required documents. For each document, identify: 1. Document name (brief but descriptive) 2. Document type (exactly one of: STANDARD, EXPERIENCE, CUSTOM) - STANDARD: Standard Company documents like company registrations/incorporation, certificates, accreditations, PAN, GST, MSME certificate, employee details, Team CVs, Turn over & financial documents etc. that the company already has - EXPERIENCE: Past work experience documents like work orders, completion certificates, PO, contracts etc. - CUSTOM: Documents to be created specifically for this bid (declarations, proposals, cover letter etc.) 3. Description of what the document should contain IMPORTANT EXCLUSION RULE: DO NOT include any document that is an Annexure, Format, Form, or Proforma specifically provided in the RFP document with a proper name or number (e.g., "Annexure-I", "Format A", "Form 6", "Proforma-B"). These annexure/format documents will be handled separately. Only extract STANDARD, EXPERIENCE, and CUSTOM documents that the bidder needs to prepare or already possesses. ADDITIONAL NOTES: a) No two documents should be mentioned in one entry. Each document should be a separate entry in the list. DO NOT repeat any same document entry in the output. b) If a document name is 'Additional Document 1, 2, 3 or 4 (Requested in ATC)', drop it. These are documents with generic description like 'Additional document format as specified in ATC'. These documents should not be included in the final list of documents. c) If a document requirement says "as per Annexure X" or "in Format Y" or "use Form Z", do NOT include it in your output - these are annexure-based documents that will be handled separately. Tender context for reference: SCOPE OF WORK SUMMARY: z Not providedz# ELIGIBILITY CRITERIA SUMMARY: z* Document requirements text: a Return your analysis as a JSON array of objects with these keys: - "name": String (Document name) - "type": String (One of: STANDARD, EXPERIENCE, CUSTOM) - "description": String (Detailed description of the document) Make sure to identify every required document (excluding annexures/formats/forms), even if it's mentioned in passing or in a complex format. rr;enabled rC budget_tokenszrYou are an expert in analyzing tender documents. Extract the requested information accurately in JSON format only.r@rMrQrRrSthinkingrTrUK ************************************************* 🧠 Minaions Thinking: ropen_llmrTrQrUz```json\s*(.*?)\s*```z\[\s*\{.*\}\s*\]r<F[T]zLFailed to parse LLM response as JSON, trying to extract individual documentsu 👨‍💻 MinAIons identified z required documentsu 📄Document : nameUnknownz - Type: rCsource_documentz.[\w\-_.]+\.(?:pdf|doc|docx|txt|xls|xlsx|PDF)\bz Found in: z/Error identifying required documents with LLM: )*loggergetwarning llm_modelr_rUr`rxinforOrrAopenaichat completionsrchoicesmessageresearchDOTALLgroupsplitstrip startswithappendendswithjoinjsonloadsJSONDecodeErrorextract_documents_from_textrW enumerater.r7findall IGNORECASErderrorstrsimple_document_extraction)r{process_logger document_info scope_of_workeligibility_criteriarprr response_text json_matchjson_strlines json_linesstartedline required_docsidocpatternmatchesrsr,r,r-identify_required_documentss  "-          0 rrAcCsg}|d}i}|D]E}|}td|}|r,|r$d|vr$||d|di}q td|}|r>|r>|d|d<q td|}|rP|rP|d|d<q q |r\d|vr\|||S) z Helper function to extract document information from text when JSON parsing fails Args: text (str): The text response from Claude Returns: list: List of document dictionaries r<z!(?:^|\s)(?:Document|Name):\s*(.+)rr;z,(?:^|\s)Type:\s*(STANDARD|EXPERIENCE|CUSTOM)rCz(?:^|\s)Description:\s*(.+) description)rrrrrr)rAdocsr current_docr name_match type_match desc_matchr,r,r-rs.        rrcsg}|d}|D]@}|}|sq td|rItdd|tj}tfdddDr1tj}ntfdddDr?tj }| |d d q |S) z Simple fallback method to extract document requirements when LLM fails Args: document_info (str): Document requirements text Returns: list: List of basic document dictionaries r<u^(\d+\.|\-|\*|\•|\–) r:c3|] }|vVqdSNlower.0termdoc_namer,r- z-simple_document_extraction..) certificate registrationpangstmsmeisocmmiz balance sheetzincome tax returnz audit reportc3rrrrrr,r-rr)z work orderzcompletion certificater0 portfolioN)rrCrr) rrrmatchsubr.r6anyr4r5r)rrrrdoc_typer,rr-rs*  rc Cstjgtjgi}tj|d}tj|r:t|D]}|dr9|tj |tj||t tj||dqtj|d}tj|rlt|D]}|drk|tj |tj||t tj||dqLt dt |tjdt |tjd|S)z Get a list of available company documents in the repository Returns: dict: Dictionary mapping document types to lists of available documents Standard_Documents)z.pdfz.docxz.jpgz.pngz.xlsxz.csv)rrvrExperience_DocumentsFound z standard documents and z experience documents)r.r4r5rurvrrwlistdirrrget_document_descriptionrrrW)company_docs_dir company_docs std_doc_pathfile exp_doc_pathr,r,r-get_available_company_documentss6          r file_pathcCs|d}tj|r't|ddd}|WdS1s"wYtj|}tj|d}|ddd d}|S) z Get description for a document based on filename or content Args: file_path (str): Path to the document Returns: str: Document description z.descrrGencodingNr_ -) rurvrwrVr]rbasenamesplitextreplace)r desc_pathffilenamerr,r,r-rs   rcCs|stddStdt|dgd}t|ddd}tj||d }|||WddS1s9wYdS) zWrites a list of dictionaries to a CSV file. Args: data: A list of dictionaries. filename: The name of the CSV file to write to. u3❌ No required documents found in the RFP details.Nu 📄 z3 documents identified to be submitted for this bid.)rrCrrrX isSelectedwr:)newline) fieldnames)r[rWrVcsv DictWriter writeheader writerows)rJrrcsvfilerlr,r,r-write_list_of_docs_to_csv*s "rbid_dirr company_inforcCs|durt} tj|d}tj|d}tj|r8t|ddd }t|}Wdn1s2wYn tdtddS| d d d } tj|d } tj | d dt j t j t jt jfD]} tj tj| | d dqb|} t| tj|dt|} td| gggd}g}| D]}d}d}td||ddkrt|| | |\}}n0|ddkrt|| | | |\}}n|ddkrt|||| | |}n|ddkrt|||| ||}|r|||s|r|rtj|| nd }|d|d|d|d|d|d|d|ddq|d|d|d|d|dd ddq|d |d!t|d|d"t||d#t|d|drh|d$d%|d| ||fS)&Ntender_analysisztender_analysis.jsonrrGruA❌ Looks like this RFP has not been analysed by Minaions before.zNPlease check the RFP directory path or analyze the RFP through Minaions first.z/final/docs/directoryr~r:rO final_docsTexist_okzrequired_documents.csvz"Available company documents are: )preparedmissingindexzRequired Document:rCr4r5r6r7rr)rrCrvrPrepared)rrCrvstatusrMissingu(📚 Bid documents preparation completedu📃 Prepared documents: u#📎 Referenced company documents: u⚠️ Missing documents: u🔺 Missing documents: z, )rrurvrrwrVrloadr[rmakedirsr.r4r5r6r7rrrprocess_standard_documentprocess_experience_documentgenerate_custom_documentprocess_annexure_formatextendrelpathrrWr)rrrrrextracted_info_pathextracted_info_filerr{rfinal_docs_dirrrequired_documentsavailable_documentsdocument_statusreferenced_company_docsreq_doc document_pathreferenced_doc_inforel_pathr,r,r-prepare_bid_documentsBs              rrrrc Cs|durt} |d|d|dg}|s |ddSd|dd|dd }t|dd D]\}}|d |d d |dd|d7}q5|d7}ztdkrntjjt dddd|dgd}|j dj } ntdkrt jjjtdddd|dgd}|jdjj } |d| | dkr|d|dWdStd| } g} | D]4} z)t| d } d| krt|krnn| || td|| dWqtyYqw| r.|dt| d |dg}| D],}|tj|d!|d!tjtj|d|dd"d#|d$tj|d!qd|fWS|d%|dWdStyX}z| d&t!|WYd}~dSd}~ww)'Nu&🕵️ Processing standard document: rr/zNo standard documents availableNNz You are an expert in government tender bidding and document matching. I need to find the most relevant company standard documents that match the following requirement: REQUIRED DOCUMENT: Name:  Description: rze Here are the available standard company documents (number, filename, and description): dr<r;. ra Please identify ALL standard documents that are relevant to the required document. Consider document types, certifications, registrations, and any keywords that indicate relevance. Return only the numbers of the relevant documents separated by commas, in order of relevance. If no documents are relevant, return "NONE". For example: "3,7,1" or "5" or "NONE" NOTE: PLEASE DO NOT RESPOND WITH ANY ADDITIONAL COMMENTARY OR INFORMATION OTHER THAN THE NUMBERS OF RELEVANT DOCUMENTS SEPARATED BY COMMAS. rrzhYou are an expert in analyzing tender documents and matching company standard documents to requirements.r@rMrPrrTrz2Minaions response for standard document matching: NONEz*No relevant standard documents found for: \d+zFound relevant document: rz$ relevant standard document(s) for: rvr:r local_pathrCcategoryrequired_doc_namerzReferencing standard document: z'No valid standard documents found for: z+Error finding relevant standard documents: )"rrrrrrr_rUr`rxrOrArrrrrrrupperrrintrWr ValueErrorrurvrr.r4rdrr)rrrr standard_docsrprrrrrrankings relevant_docsrankrreferenced_docsrsr,r,r-rs   (        rrc Cs*|durt} |d|d|rSt||tj|}|rSg}|D],}|tj|d|dtjtj|d| ddd|dtj|dq"d|fSt ||tj}|rtj|d|dtjtj|d| dddg}|dtj|dd|fS| d|dd S) Nu(🕵️ Processing experience document: rrvrr:r'z!Referencing experience document: z+No matching experience document found for: r ) rr$select_relevant_experience_documentsr.r5rrurvrrfind_best_document_matchr) rrrrrr0r2r best_matchr,r,r-r*sH    ravailable_docsc Cs|sdSd}d}t|d}|D],}t|d|d}||}t|tt|d}||kr@|}|}q|dkrG|SdS)a Find the best matching document from available documents Args: req_doc (dict): Required document information available_docs (list): List of available documents Returns: dict: Best matching document, or None if no good match Nrrrr;g333333?)setrr intersectionrWmax) rr6r5 best_score req_termsr doc_terms common_termsscorer,r,r-r4gs  $ r4experience_docsc Cs|r|sgSd|ddd|dd|dd}t|dd D]\}}|d |d d |dd |d7}q"|d7}zptdkr[tjjtdddd|dgd}|jdj}ntdkryt j j jt dddd|dgd}|j djj}td|}g} |D](} zt| d } d| krt|krnn| || WqtyYqw| WSty} ztdt| gWYd} ~ Sd} ~ ww)aY Select relevant experience documents based on scope of work Args: req_doc (dict): Required document information experience_docs (list): List of available experience documents scope_of_work (str): Scope of work for context Returns: list: Ranked list of relevant experience documents z You are an expert in government tender bidding. I need to select the most relevant past experience documents for a tender with the following scope of work: SCOPE OF WORK: NrzJ # Limit scope to avoid token limit issues The tender requires: rz - rzV Here are the available experience documents (filename and description): r<r;r#ra Please rank the top 3 most relevant experience documents for this tender requirement, considering relevance to the scope of work. Return only the numbers of the documents in order of relevance, separated by commas. For example: "5,12,3" rr$rz\You are an expert in analyzing tender documents and selecting relevant experience documents.r@rMrPrrTrr&z/Error selecting relevant experience documents: )rrr_rUr`rxrOrArrrrrrrrrr,rWrr-rdrrr) rr?rrprrrrrr/ ranked_docsr1rrsr,r,r-r3s`   (    r3cCs|durt} |d|d|ddd}|ddd}d|dd|dd |d d |dd d |dd d|ddd|d}ztdkrvtjjtddddddd|dgd} |d| jdj | jdj } ntdkrt j j jtdddd|dgd } | jdjj} tj|tj} td!d|dd"d#} tj| | d$} tjd%d| tjd&} td'd| } t| d(d)d* }|| Wdn1swY|d+tj| | WSty }z|d,t |WYd}~dSd}~ww)-Nu!🤖 Generating custom document: rrr:rOz Payment termszY You are an expert in government tender document preparation. I need you to create a z for a tender bid. The document should be professional, complete, and follow standard formats. Document Required: r!rzC Relevant Tender Information: SCOPE OF WORK: iz$ ELIGIBILITY CRITERIA: z PAYMENT TERMS: rz& Bidder Company Details: a Please generate the complete document text in a professional format. Include: - Appropriate header with company letterhead elements - Date and reference number - Professional salutation and closure - All necessary declarations or statements - Any legal language typically required for such a document - Proper formatting with bold, line breaks, paragraphs and tabs etc using HTML tags. The document should be ready to print and sign without further modifications. PLEASE NOTE that: 1. The output should be in portrait A4 size PDF compatible HTML ONLY. 2. For tables in the output response, please use HTML table tags. 3. For any bullet points or serial points, please put them in new lines instead of putting them in one blob of text. 4. DO NOT make up or create imaginary details for Company's critical information like employee details, designations, previous projects etc, unless provided explicitly in 'Bidder Company Details'. rrr;rrr=You are an expert in preparing professional tender documents.r@rMrrrrrTr[^\w\s-]rr.html```htmlflags```rrGrzGenerated custom document: z"Error generating custom document: )!rrrrr_rUr`rxrOrrArrrrrrrurvrr.r6rrrrrrVr\rrdrr)rr{rrrr eligibility payment_termsrprr document_textdest_dir safe_name dest_pathrrsr,r,r-rsv    ( rcCs@|r|dkr dStdd|}dd|D}t|S)zi Count words in a given text string. Removes extra whitespace and handles basic punctuation. r:rz\s+rcSsg|]}|r|qSr,r,)rwordr,r,r- Vszcount_words..)rrrrrW)rA cleaned_textwordsr,r,r- count_wordsJs rSorg_doc_file_path user_promptc CsBtd|zt|ddd }|}Wdn1swYWn&ty2d|YStyJ}z dt|WYd}~Sd}~ww|dd d }|d d d } |d d d } d } d} d} | t|7} | t|7} | t|7} | t| 7} | t| 7} td| | d} d}d|d|d|d| d| d }zNt dkrt j d|gt j dddd}|j}n6t dkrtjjtdd|d|d gd!}|jdj}nt d"krtjjjtd#|d d|d gd$}|jdjj}Wnty}ztd%t|WYd}~d&Sd}~wwt|jd'd'd(t d)}t|j!}d*|d+|d,}t"j#$|t%j&}t"j#$||}|'(d-sNd.|d/}|}t)j*d0d |t)j+d1}t)*d2d |}z't|d3dd }|,|Wdn1sxwYW|| fSW|| fSty}z d4t|WYd}~Sd}~ww)5aY Regenerate a document using Claude Sonnet for bid submission purposes. Args: org_doc_file_path (str): Path to the original document file user_prompt (str): User's instructions on what needs to be changed company_info (str): Bidder company's information and details final_docs_dir (str): Directory to save the final document scope_of_work (str): Scope of work from the RFP documents eligibility_criteria (str): List of eligibility criteria for bidders Returns: str: Path to the generated document file or error message z%Regenerating the requested document: rrGrNz+Error: Original document file not found at z!Error reading original document: r}r:rOr~rgg{Gzt?rzYou are an expert document writer specializing in creating professional bid submission documents for tenders and RFPs. Your task is to regenerate, recreate, or rephrase documents based on user requirements while maintaining professionalism and accuracy.z} Please regenerate the following document based on the user's requirements and provided information: **ORIGINAL DOCUMENT:** z' **USER'S REQUIREMENTS FOR CHANGES:** z" **BIDDER COMPANY INFORMATION:** z **SCOPE OF WORK FROM RFP:** z **ELIGIBILITY CRITERIA:** a **IMPORTANT FORMATTING AND CONTENT REQUIREMENTS:** 1. The output should be in portrait A4 size PDF compatible HTML ONLY. 2. For tables in the output response, please use HTML table tags with proper styling. 3. For any bullet points or serial points, please put them in new lines instead of putting them in one blob of text. 4. DO NOT make up or create imaginary details for Company's critical information like employee details, designations, previous projects etc, unless provided explicitly in 'Bidder Company Details'. 5. Maintain professional tone and format suitable for bid submission, ensuring that the user's requirements for changes are properly addressed. 6. Ensure the document addresses relevant aspects from the scope of work and eligibility criteria where applicable. 7. Use proper HTML structure with appropriate CSS styling for A4 portrait format. Please provide the complete regenerated document in HTML format that can be converted to PDF while maintaining A4 portrait layout. rgemini-2.5-flash-preview-04-17r>皙?max_output_tokensrSrQcontentsconfigrr@rMrPrrTrzError calling Claude API: )NrT)parentsrz %Y%m%d_%H%M%S regenerated_rrDza Regenerated Bid Document z rErFrHrz$Error saving re-generated document: )-r[rVr]rcrdrrrSroundr gemini_modelgenerate_contentrGenerateContentConfigrAr_rUr`rxrOrrrrrrrrrmkdirrnowstrftimestemrurvrr.r8rrrrrr\)rTrUrrr{roriginal_documentrsrrr regen_costbase_cost_per_word total_words system_promptrprrrKgenerated_content timestamporiginal_filenameoutput_filenamerLrg html_templater,r,r-regenerate_documentZs           8;  rrlog_textc Cs~i}d}t||tj}|D].}|d}t|d}t|d}t|d}tt||d} |||| d||<q|S)aq Parse the annexure scan log and extract all annexure information. Args: log_text: The raw log output from the annexure scanning script Returns: Dictionary mapping annexure names to their details: { "ANNEXURE XIV": {"start": 74, "end": 75, "page_count": 2, "pages": [74, 75]}, ... } uF✅\s*(ANNEXURE\s*[\w\-]+):\s*pages\s*(\d+)-(\d+)\s*\((\d+)\s*pages?\)rr;rV)startend page_countrX)rrrrr+r,listrange) rs annexuresrrr annexure_name start_pageend_pagerwrXr,r,r-parse_annexure_log#s    r~r{annexure_numberannexure_formatc Cs|durt} |rd|n|}d|d|d|d}ztdkr3tjd|gtjdd d d } | j} nFtd kr]tjj t d dddddd|dgd} | d| j dj | j dj} ntdkrytjjj tdddd|dgd} | jdjj } t| |} tjdd| tjd} tdd| } tj|tj} tdd|d d!} tj| | d"}tj| d#d$t |d%d&d' }|!| Wdn1swY| d(tj"||WSt#y}z|$d)t%|WYd}~dSd}~ww)*N Annexure z You are an expert in government tender document preparation. I need to fill out an annexure format for a bid submission. I've extracted the exact format from the tender document. Required Document: z2 Here is the exact format from the RFP: zc Please fill this format with appropriate information from this Company Information: ae Follow EXACTLY the original layout, tables, and structure, but fill in all blank fields. If there are tables in the format, then please use keys like | or _ or - or tabs and spaces to represent the exact format of the table in the output. Again please fill in ALL fields with appropriate information for this type of tender from the company information provided above. Completely replace the place holder text in the format with the actual information, wherever found. If a field needs specific technical information not provided here, use the string ''. DO NOT make up Company's critical information like employee details, designations, previous projects etc, unless provided explicitly in Bidder Company Details. IMPORTANT: Maintain the EXACT formatting and layout of the original. Return ONLY the filled document. rrWr>rXrYr[rrr;rrrzzYou are an expert in preparing professional tender annexure documents. Fill the exact format with appropriate information.r@rMrrrrrTrrEr:rFrHrCrrrDTrrrGru(✅ Generated filled annexure document: u0🛑 Error generating filled annexure document: )&rrrarbrrcrAr_rUr`rxrrOrrrrrrrrzrrrrurvrr.r7rrr rVr\rrdrr)r{rrrrrer annexure_descrprrfilled_documentformatted_documentrLrMrNrrsr,r,r-generate_filled_annexureKsx    "r file_descrIreq_docsc Cs|d|d|d|}d|d|d|d|d|d } ztd kr;tjjd | gtjd d dd} | j} nFtdkretj j t ddddddd| dgd} |d| j dj | j dj} ntdkrtjjj tdddd| dgd} | jdjj } tj|tj} tdd |d!d"} tj| | d#}tj| d$d%tjd&d | tjd'} td(d | } t|d)d*d+ }| | Wd,n1swY|d-tj!||WSt"y}z|#d.t$|WYd,}~d,Sd,}~ww)/a Fallback function to generate an annexure document when the exact format can't be found Args: req_doc (dict): Required document information final_docs_dir (str): Directory for final documents Returns: str: Path to the generated document z,Using fallback method to generate annexure: rrz You are an expert in government tender document preparation. I need to create an annexure document for a bid submission, but I dont have the exact format for this document. Required Document: a4 Please create a standard professional format typically used for this type of annexure in government tenders. This should look like a authentic, professional government tender annexure. To create this document, you may please use the appropriate information from this Company Information: zf Other related information about this tender/RFP is as following: Eligibility Criteria: z Scope of Work: z8 Documents required to be sumitted in the bid: a The format should include: - Professional header with annexure title - All standard fields typically found in this type of annexure - Appropriate spaces for signatures, dates, and stamps - Any declarations or statements typically required - Proper formatting with bold, line breaks, paragraphs and tabs etc using HTML tags. Please create a complete and professional document ready for submission without further modifications. PLEASE NOTE that: 1. The output should be in portrait A4 size PDF compatible HTML ONLY. 2. For tables in the output response, please use HTML table tags. 3. For any bullet points or serial points, please put them in new lines instead of putting them in one blob of text. 4. DO NOT make up or create imaginary details for Company's critical information like employee details, designations, previous projects etc, unless provided explicitly in 'Bidder Company Information'. rzgemini-2.5-flashr>rXrYr[rrr;rrrrBr@rMrrrrrTrrCr:rrrDTrrErFrHrrGrNu(✅ Generated Annexure Custom document: z-Error generating fallback annexure document: )%rr gemini_clientmodelsrbrrcrAr_rUr`rxrOrrrrrrrrurvrr.r7rrrrr rrVr\rrdrr)r{rrrrIrrrrrprrrKrLrMrNrrsr,r,r-generate_annexure_fallbacks|  + rc Cs|durt} |d|d|d}|dd}|dd}|dg} |d|d |d | |d d d } |dd d } |dd d } td|tj} | r^| dnd}|d|d||d|d}d}tt | d}|D]F}|d|d|d|j |dkr||j vrt j |d}t j |d}t|| |}|r|}|d|j n |d|j q|rt|||||||S|dt||||| | | |S)Nu!🤖 Processing annexure format: rrrrzNo Description givenrXz Trying to find annexure z in file z on pages: rr:rOr}r~zP(?:annexure|format|form|proforma|checklist|annex)\s*[-\s]*([\dIVXivx]+|[a-zA-Z])r;z( annexure_name and annexure_number are: z and u 🔍 Looking for annexure z**/*.pdfz Processing Files: z with rztemp_annexure.pdfu🎉 Found annexure content in zAnnexure not found in document zfCould not find annexure format in any tender document. Generating the document as custom document now.)rrrrrrrrrxrglobrrurvrrtrrr)rr{rrrrr{ source_hintrrXrIrrannexure_matchrannexure_content source_file all_pdf_filesrhout_dir annex_pathr,r,r-r*sJ       rr)Mrushutilrr anthropicloggingPyPDF2rrpathlibrrrtypingrrr r r r argparsesysrrEdotenvr getenvrrrrrgoogle.generativeai generativeaigenairrr basicConfigINFO getLoggerrrBASE_DIRCOMPANY_REPOSITORYCLAUDE_API_KEYrr Anthropicr_GenerativeModelrarxclaude_model_literr.rtrzrrrrrrrrrrr4r3rrSrrr~rrrr,r,r,r-s                 NT$-,',o y="$$Rm"J$(,i(v