Method gen_initial_report

papersolver.py:330–397

(self)

        return text

    def gen_initial_report(self):
        num_attempts = 0
        arx = ArxivSearch()
        section_scaffold = str()
        #  1. Abstract 2. Introduction, 3. Background, 4. Methods, 5. Experimental Setup 6. Results, and 7. Discussion
        for _section in ["scaffold", "abstract", "introduction", "related work", "background", "methods", "experimental setup", "results", "discussion"]:
            section_complete = False
            if _section in ["introduction", "related work", "background", "methods", "discussion"]:
                attempts = 0
                papers = str()
                first_attempt = True
                while len(papers) == 0:
                    att_str = str()
                    if attempts > 5:
                        break
                    if not first_attempt:
                        att_str = "This is not your first attempt please try to come up with a simpler search query."
                    search_query = query_model(model_str=f"{self.llm_str}", prompt=f"Given the following research topic {self.topic} and research plan: \n\n{self.plan}\n\nPlease come up with a search query to find relevant papers on arXiv. Respond only with the search query and nothing else. This should be a a string that will be used to find papers with semantically similar content. {att_str}", system_prompt=f"You are a research paper finder. You must find papers for the section {_section}. Query must be text nothing else.", openai_api_key=self.openai_api_key)
                    search_query.replace('"', '')
                    papers = arx.find_papers_by_str(query=search_query, N=10)
                    first_attempt = False
                    attempts += 1
                if len(papers) != 0:
                    self.section_related_work[_section] = papers
            while not section_complete:
                section_scaffold_temp = copy(section_scaffold)
                if num_attempts == 0: err = str()
                else: err = f"The following was the previous command generated: {model_resp}. This was the error return {cmd_str}. You should make sure not to repeat this error and to solve the presented problem."
                if _section == "scaffold":
                    prompt = f"{err}\nNow please enter the ```REPLACE command to create the scaffold:\n "
                else:
                    rp = str()
                    if _section in self.section_related_work:
                        rp = f"Here are related papers you can cite: {self.section_related_work[_section]}. You can cite them just by putting the arxiv ID in parentheses, e.g. (arXiv 2308.11483v1)\n"
                    prompt = f"{err}\n{rp}\nNow please enter the ```REPLACE command to create the designated section, make sure to only write the text for that section and nothing else. Do not include packages or section titles, just the section content:\n "
                model_resp = query_model(
                    model_str=self.model,
                    system_prompt=self.system_prompt(section=_section),
                    prompt=f"{prompt}",
                    temp=0.8,
                    openai_api_key=self.openai_api_key)
                model_resp = self.clean_text(model_resp)
                if _section == "scaffold":
                    # minimal scaffold (some other sections can be combined)
                    for _sect in ["[ABSTRACT HERE]", "[INTRODUCTION HERE]", "[METHODS HERE]", "[RESULTS HERE]", "[DISCUSSION HERE]"]:
                        if _sect not in model_resp:
                            cmd_str = "Error: scaffold section placeholders were not present (e.g. [ABSTRACT HERE])."
                            if not self.supress_print: print("@@@ INIT ATTEMPT:", cmd_str)
                            continue
                elif _section != "scaffold":
                    new_text = extract_prompt(model_resp, "REPLACE")
                    section_scaffold_temp = section_scaffold_temp.replace(f"[{_section.upper()} HERE]", new_text)
                    model_resp = '```REPLACE\n' + copy(section_scaffold_temp) + '\n```'
                    if "documentclass{article}" in new_text or "usepackage{" in new_text:
                            cmd_str = "Error: You must not include packages or documentclass in the text! Your latex must only include the section text, equations, and tables."
                            if not self.supress_print: print("@@@ INIT ATTEMPT:", cmd_str)
                            continue
                cmd_str, latex_lines, prev_latex_ret, score = self.process_command(model_resp, scoring=False)