Resumable intermediates #2
+19
-7
@@ -1,9 +1,9 @@
|
|||||||
local timing = {}
|
local timing = {
|
||||||
|
entries = {}
|
||||||
|
}
|
||||||
|
|
||||||
function timing.timer()
|
local function to_minutes(t) -- floored to tenths
|
||||||
return setmetatable({
|
return math.floor( t / 60 * 10 ) / 10
|
||||||
entries = {},
|
|
||||||
}, timing)
|
|
||||||
end
|
end
|
||||||
|
|
||||||
function timing:start()
|
function timing:start()
|
||||||
@@ -15,8 +15,20 @@ function timing:stop()
|
|||||||
local entry = self.entries[#self.entries]
|
local entry = self.entries[#self.entries]
|
||||||
entry.stop_time = os.time()
|
entry.stop_time = os.time()
|
||||||
|
|
||||||
-- delta in minutes, floored to tenths
|
return to_minutes(entry.stop_time - entry.start_time) -- return delta
|
||||||
return math.floor( (entry.stop_time - entry.start_time) / 60 * 10 ) / 10
|
end
|
||||||
|
|
||||||
|
function timing:print_report()
|
||||||
|
local minimum, maximum, sum = math.huge, -math.huge, 0
|
||||||
|
for _, data in pairs(self.entries) do
|
||||||
|
local delta = data.stop_time - data.start_time
|
||||||
|
if delta > maximum then maximum = delta end
|
||||||
|
if delta < minimum then minimum = delta end
|
||||||
|
sum = sum + delta
|
||||||
|
end
|
||||||
|
print("Total: " .. to_minutes(sum) .. " minutes.")
|
||||||
|
print("Averge: " .. to_minutes(sum / #self.entries) .. " minutes. Fastest: "
|
||||||
|
.. to_minutes(minimum) .. " minutes. Slowest: " .. to_minutes(maximum) .. " minutes.")
|
||||||
end
|
end
|
||||||
|
|
||||||
return timing
|
return timing
|
||||||
|
|||||||
+42
-16
@@ -2,7 +2,8 @@
|
|||||||
|
|
||||||
package.path = (arg[0]:match("@?(.*/)") or arg[0]:match("@?(.*\\)")) .. "lib" .. package.config:sub(1, 1) .. "?.lua;" .. package.path
|
package.path = (arg[0]:match("@?(.*/)") or arg[0]:match("@?(.*\\)")) .. "lib" .. package.config:sub(1, 1) .. "?.lua;" .. package.path
|
||||||
local utility = require "utility"
|
local utility = require "utility"
|
||||||
-- TODO import timing library
|
local prompts = require "prompts"
|
||||||
|
local timing = require "timing"
|
||||||
|
|
||||||
local config = utility.get_config("read-only")
|
local config = utility.get_config("read-only")
|
||||||
if not config.llm_covers then config.llm_covers = {} end
|
if not config.llm_covers then config.llm_covers = {} end
|
||||||
@@ -10,7 +11,17 @@ if not config.llm_covers.calibre_location then config.llm_covers.calibre_locatio
|
|||||||
if not config.llm_covers.default_model then config.llm_covers.default_model = "gemma4:12b-mlx" end
|
if not config.llm_covers.default_model then config.llm_covers.default_model = "gemma4:12b-mlx" end
|
||||||
if not config.llm_covers.maximum_bytes then config.llm_covers.maximum_bytes = 40000 end
|
if not config.llm_covers.maximum_bytes then config.llm_covers.maximum_bytes = 40000 end
|
||||||
|
|
||||||
-- TODO import prompts, use new names from fork
|
local read_all = function(file_name)
|
||||||
|
return utility.open(file_name, "r", function(file)
|
||||||
|
return file:read("*all")
|
||||||
|
end)
|
||||||
|
end
|
||||||
|
local write_all = function(file_name, text)
|
||||||
|
return utility.open(file_name, "w", function(file)
|
||||||
|
file:write(text)
|
||||||
|
file:write("\n")
|
||||||
|
end)
|
||||||
|
end
|
||||||
|
|
||||||
local strip_reasoning = function(text, reasoning_lines)
|
local strip_reasoning = function(text, reasoning_lines)
|
||||||
if not reasoning_lines then reasoning_lines = {} end
|
if not reasoning_lines then reasoning_lines = {} end
|
||||||
@@ -31,18 +42,27 @@ local strip_reasoning = function(text, reasoning_lines)
|
|||||||
end
|
end
|
||||||
end
|
end
|
||||||
|
|
||||||
-- TODO import and rewrite send_prompt to use new timing library
|
local send_prompt = function(text, model)
|
||||||
|
if type(text) == "table" then text = table.concat(text, "\n") end
|
||||||
|
|
||||||
local read_all = function(file_name)
|
local tmp_file_name = utility.tmp_file_name()
|
||||||
return utility.open(file_name, "r", function(file)
|
utility.open(tmp_file_name, "w", function(file)
|
||||||
return file:read("*all")
|
|
||||||
end)
|
|
||||||
end
|
|
||||||
local write_all = function(file_name, text)
|
|
||||||
return utility.open(file_name, "w", function(file)
|
|
||||||
file:write(text)
|
file:write(text)
|
||||||
file:write("\n")
|
|
||||||
end)
|
end)
|
||||||
|
|
||||||
|
timing:start()
|
||||||
|
-- word wrap breaks the raw output badly, so I need to implement my own for terminal output somehow
|
||||||
|
local output = utility.capture_safe("cat " .. tmp_file_name:enquote() .. " | ollama run " .. (model or default_model) .. " --nowordwrap")
|
||||||
|
os.execute("ollama stop " .. (model or default_model)) -- NOTE this makes things slower, but more stable
|
||||||
|
local delta = timing:stop()
|
||||||
|
|
||||||
|
print("Took " .. delta .. " minutes.")
|
||||||
|
os.execute("rm " .. tmp_file_name)
|
||||||
|
if not output then error("ollama failed to generate output") end
|
||||||
|
|
||||||
|
output = output:sub(1, -2) -- strip extra newline from utility.capture_safe
|
||||||
|
output = strip_reasoning(output)
|
||||||
|
return output
|
||||||
end
|
end
|
||||||
|
|
||||||
local make_directories = function()
|
local make_directories = function()
|
||||||
@@ -166,7 +186,7 @@ local condense_summary = function(name, data, sections)
|
|||||||
print("Loaded condensed summary segment. " .. #sections .. " sections remaining.")
|
print("Loaded condensed summary segment. " .. #sections .. " sections remaining.")
|
||||||
else
|
else
|
||||||
print("Condensing summary. " .. #sections .. " sections remaining.")
|
print("Condensing summary. " .. #sections .. " sections remaining.")
|
||||||
local text = send_prompt(squish_partials_prompt .. table.concat(sections_slice, "\n\n"))
|
local text = send_prompt(prompts.combine_summaries .. table.concat(sections_slice, "\n\n"))
|
||||||
condensed_sections[#condensed_sections + 1] = text
|
condensed_sections[#condensed_sections + 1] = text
|
||||||
print(#text .. " characters added to final context.")
|
print(#text .. " characters added to final context.")
|
||||||
write_all(intermediate_condensation_file, text)
|
write_all(intermediate_condensation_file, text)
|
||||||
@@ -199,7 +219,7 @@ local generate_summary = function(name, data)
|
|||||||
else
|
else
|
||||||
print("Processing section " .. (i + 1) .. " of " .. math.floor(data.extracted_file_size/config.llm_covers.maximum_bytes + 1))
|
print("Processing section " .. (i + 1) .. " of " .. math.floor(data.extracted_file_size/config.llm_covers.maximum_bytes + 1))
|
||||||
local section = text:sub(i * config.llm_covers.maximum_bytes, (i + 1) * config.llm_covers.maximum_bytes - 1)
|
local section = text:sub(i * config.llm_covers.maximum_bytes, (i + 1) * config.llm_covers.maximum_bytes - 1)
|
||||||
section = send_prompt(partial_prompt .. section)
|
section = send_prompt(prompts.section_summarization .. section)
|
||||||
sections[#sections + 1] = section
|
sections[#sections + 1] = section
|
||||||
print(#section .. " characters added to intermediate context.")
|
print(#section .. " characters added to intermediate context.")
|
||||||
write_all(intermediate_section_file, section)
|
write_all(intermediate_section_file, section)
|
||||||
@@ -238,17 +258,23 @@ local generate_cover_briefs = function(books)
|
|||||||
end
|
end
|
||||||
|
|
||||||
print("Generating cover brief.")
|
print("Generating cover brief.")
|
||||||
text = send_prompt(cover_brief_prompt .. text)
|
text = send_prompt(prompts.cover_brief .. text)
|
||||||
|
|
||||||
local cover_brief_file = "cover_briefs/" .. name .. ".txt"
|
local cover_brief_file = "cover_briefs/" .. name .. ".txt"
|
||||||
write_all(cover_brief_file, text)
|
write_all(cover_brief_file, text)
|
||||||
write_all("for_gemini/" .. name .. ".txt", "Title: " .. name .. gemini_prompt .. text)
|
write_all("for_gemini/" .. name .. ".txt", "Title: " .. name .. prompts.for_gemini .. text)
|
||||||
data.cover_brief_file = cover_brief_file
|
data.cover_brief_file = cover_brief_file
|
||||||
end
|
end
|
||||||
end
|
end
|
||||||
|
|
||||||
make_directories()
|
make_directories()
|
||||||
generate_cover_briefs(get_books())
|
|
||||||
|
local books = get_books()
|
||||||
|
convert_ebooks(books)
|
||||||
|
generate_cover_briefs(books)
|
||||||
|
|
||||||
|
print("")
|
||||||
|
timing:print_report()
|
||||||
|
|
||||||
-- ebook_file, extracted_file, extracted_file_size,
|
-- ebook_file, extracted_file, extracted_file_size,
|
||||||
-- intermediate_file, condensed_intermediate_file, cover_brief_file
|
-- intermediate_file, condensed_intermediate_file, cover_brief_file
|
||||||
|
|||||||
Reference in New Issue
Block a user